© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91449
    Prev
    Next
    INDEX
    Explanations

    version 2 or 3

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

    The neuron consistently lights up on tokens that are numbers or numeric references (e.g. verse citations, years, version numbers).

    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
     magg
    -0.77
    諛
    -0.72
     triggered
    -0.69
     исправ
    -0.69
    对外
    -0.69
     unacc
    -0.68
     verpflichtet
    -0.67
    iosas
    -0.67
    گاب
    -0.67
     isnt
    -0.66
    POSITIVE LOGITS
    Jn
    0.97
    rators
    0.91
     şə
    0.90
    ėjas
    0.84
     abide
    0.84
    RELATION
    0.81
     pêche
    0.79
     déli
    0.77
    ンドン
    0.77
     porcelana
    0.76
    Activations Density 0.003%

    No Known Activations