© 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. 106881
    Prev
    Next
    INDEX
    Explanations

    chap, chapel, chop, chapman

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

    The neuron consistently activates on tokens containing the letter sequence “chap” (e.g. Chap, CHAP, chap), regardless of case.

    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
    salomon
    -0.82
    ignite
    -0.82
    ILDREN
    -0.82
     veľmi
    -0.81
    DOCX
    -0.80
    ampire
    -0.79
    ángulo
    -0.75
     благода
    -0.75
     Paran
    -0.73
    timp
    -0.73
    POSITIVE LOGITS
     lavor
    0.77
    Lid
    0.76
    Rev
    0.72
     aggregation
    0.72
    純正
    0.70
    貨
    0.69
    Latest
    0.69
     lid
    0.68
     chap
    0.68
     Lid
    0.68
    Activations Density 0.011%

    No Known Activations