© 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. 58414
    Prev
    Next
    INDEX
    Explanations

    Sports and medical terms

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

    references to Firebase and other database-related technology in code and documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron strongly responds to programming identifiers (e.g. CamelCase or mixed-case names) in code or JSON rather than ordinary prose.

    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
    Gz
    -0.89
    値
    -0.85
    oskop
    -0.82
     salles
    -0.79
     stipulations
    -0.78
    debit
    -0.77
    クラウド
    -0.77
     rejuvenation
    -0.75
    リエーション
    -0.74
     dokumen
    -0.72
    POSITIVE LOGITS
     produit
    0.81
    Win
    0.79
    setProduct
    0.78
    ﾙ
    0.78
    iri
    0.77
     hacer
    0.77
    enda
    0.77
    lun
    0.75
    UTF
    0.75
    metal
    0.75
    Activations Density 0.015%

    No Known Activations