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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19706
    Prev
    Next
    INDEX
    Explanations

    file path or command components

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

    The neuron fires on numeric literals (tokens containing digits, e.g. version numbers or numeric parameter values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.98
    -
    -1.81
    '
    -1.79
    ;
    -1.73
    "
    -1.70
     agujeros
    -1.70
     those
    -1.65
    ade
    -1.63
     also
    -1.56
     maleta
    -1.53
    POSITIVE LOGITS
    哢
    1.89
    捽
    1.87
    ofition
    1.73
     ФИ
    1.70
    玊
    1.68
    ăț
    1.66
    patine
    1.66
     Können
    1.65
    ではある
    1.65
    ſelves
    1.64
    Activations Density 0.031%

    No Known Activations