© 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. 34-GEMMASCOPE-RES-131K
    7. 45478
    Prev
    Next
    INDEX
    Explanations

    and associated

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

    The neuron activates on numeric tokens (digit sequences) in the text—i.e. it detects 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
    険
    -0.88
    λους
    -0.84
     강
    -0.82
    ronym
    -0.81
    mola
    -0.79
     nvm
    -0.79
     problems
    -0.75
    vanni
    -0.75
     họ
    -0.75
     chargement
    -0.74
    POSITIVE LOGITS
    '");
    0.88
     என்
    0.79
    ));
    0.77
     tường
    0.74
    >>;
    0.73
    addError
    0.71
    рене
    0.71
     喝
    0.71
    spher
    0.71
    Если
    0.71
    Activations Density 0.001%

    No Known Activations