© 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. 83910
    Prev
    Next
    INDEX
    Explanations

    numbers or code segments

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

    The neuron primarily activates on numeric tokens (e.g. years, section numbers, pH values, indexes), i.e. sequences of digits.

    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
    addAction
    -0.79
     边
    -0.76
    <u>
    -0.76
    mittelt
    -0.73
     reeds
    -0.73
    zeli
    -0.72
    cticide
    -0.72
     zví
    -0.72
     insom
    -0.71
    vanie
    -0.71
    POSITIVE LOGITS
    bori
    0.82
    Ꮐ
    0.75
     vuoi
    0.75
    //*/
    0.74
    esses
    0.73
    //**
    0.72
     Risiken
    0.72
    བ་
    0.71
     newNode
    0.71
     materials
    0.70
    Activations Density 0.122%

    No Known Activations