© 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. 10-GEMMASCOPE-RES-131K
    7. 20986
    Prev
    Next
    INDEX
    Explanations

    may not use

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

    This neuron detects license‐header restriction clauses that forbid using the file except under specified licensing conditions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    熈
    -1.70
     vývoj
    -1.58
    حة
    -1.52
    圌
    -1.51
    \%,
    -1.51
    ȷ
    -1.50
     aussit
    -1.48
    鹇
    -1.48
    土産
    -1.47
     complies
    -1.47
    POSITIVE LOGITS
    However
    1.74
     Especially
    1.49
     folgenden
    1.47
     nächsten
    1.45
     Interestingly
    1.43
    Interestingly
    1.35
     be
    1.32
     Traditionally
    1.31
     sogenannten
    1.31
    した
    1.30
    Activations Density 0.062%

    No Known Activations