© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32933
    Prev
    Next
    INDEX
    Explanations

    Oracle database

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

    The neuron is picking up on any multi-character token (longer contiguous sequences of letters or digits), i.e. tokens above a minimal length threshold.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kaos
    -0.91
    ggg
    -0.88
    ":[
    -0.87
     devotees
    -0.87
    𝘯
    -0.86
     quella
    -0.85
    Blu
    -0.84
     coronation
    -0.83
     radiators
    -0.82
    lala
    -0.82
    POSITIVE LOGITS
     in
    1.09
    ಝ
    1.07
     from
    1.00
    codable
    0.98
    asında
    0.92
    ugía
    0.91
     toolStrip
    0.90
    嘩
    0.87
     poros
    0.86
    が上が
    0.86
    Activations Density 0.011%

    No Known Activations