© 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. 63002
    Prev
    Next
    INDEX
    Explanations

    programmatic definitions and settings

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

    This neuron activates on numeric tokens or numeric literals (e.g. version numbers, table IDs, measurements).

    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
    מלי
    -0.80
    projec
    -0.76
    noob
    -0.73
     项目
    -0.72
    iteur
    -0.70
    írez
    -0.69
    🤥
    -0.69
    competition
    -0.68
    artiste
    -0.67
    游戏的
    -0.67
    POSITIVE LOGITS
    왔
    0.69
    olu
    0.69
    acc
    0.69
    holz
    0.68
    UM
    0.67
    bon
    0.67
    instance
    0.66
    ℂ
    0.66
    trigger
    0.66
    content
    0.66
    Activations Density 0.052%

    No Known Activations