© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30992
    Prev
    Next
    INDEX
    Explanations

    Glass album Earl

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

    This neuron responds strongly to title‐ and heading‐style tokens (e.g. capitalized words at the start of sections, markers like “The,” “Big,” names, numbers, and punctuation used in headers).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ,,,,
    -0.81
     перене
    -0.74
     Aç
    -0.72
     orientations
    -0.72
     ti
    -0.71
    >>>>
    -0.71
    Frust
    -0.70
     реша
    -0.69
     tia
    -0.68
    Più
    -0.68
    POSITIVE LOGITS
     overland
    0.93
     thus
    0.84
     openly
    0.79
     foal
    0.78
     Vulnerability
    0.77
    visející
    0.77
    litter
    0.73
     STICK
    0.73
     likely
    0.71
    upné
    0.71
    Activations Density 0.051%

    No Known Activations