© 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. 117251
    Prev
    Next
    INDEX
    Explanations

    script comments and numbers

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

    The neuron fires on standalone numeric tokens—especially digits used in version numbers or years.

    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
     powod
    -0.70
    šie
    -0.68
     siedz
    -0.67
     ця
    -0.67
     decays
    -0.66
    Actividad
    -0.65
     діяльності
    -0.64
     denomina
    -0.63
    challenge
    -0.62
    ikou
    -0.62
    POSITIVE LOGITS
     Hurst
    0.84
     затра
    0.76
     Bamboo
    0.70
     SAND
    0.69
    kirch
    0.69
    pointer
    0.69
     anglaise
    0.68
     WINE
    0.68
     SOL
    0.68
     pointer
    0.67
    Activations Density 0.072%

    No Known Activations