© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56915
    Prev
    Next
    INDEX
    Explanations

    Griff/Graf name prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently fires on capitalized words beginning with the “Gri-” (or closely similar) letter sequence—e.g. Griffith, Griff, Gribble, Grafix.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    the substring "griff" or similar letter combinations, particularly in proper names like "Griffith", "Griffin", "Griff", or words like "giraffe".

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    words containing the letter cluster “grif/graf,” often in proper names.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ᶠ
    -0.74
     opleiding
    -0.72
    zied
    -0.71
    UBLIC
    -0.70
     olur
    -0.69
    纂
    -0.68
    omány
    -0.68
    ització
    -0.68
     Felix
    -0.67
     Individual
    -0.67
    POSITIVE LOGITS
    多元
    0.74
    ritten
    0.72
     escrow
    0.71
    therefore
    0.69
    を受け
    0.67
    ith
    0.67
    Griff
    0.66
     Escrow
    0.64
    avr
    0.64
     CLAR
    0.64
    Activations Density 0.040%

    No Known Activations