© 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. 112336
    Prev
    Next
    INDEX
    Explanations

    entity names in code

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

    variable names related to collections or pluralized objects (especially in programming contexts like arrays, lists, tables, or groups of objects).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     même
    -1.52
     bemerken
    -1.35
    全く
    -1.32
    从来
    -1.29
     never
    -1.24
     autores
    -1.20
    zzly
    -1.20
    baom
    -1.20
    まったく
    -1.19
    Péri
    -1.18
    POSITIVE LOGITS
     wwe
    1.44
    eeeeeeee
    1.38
    eeeeee
    1.31
     tdi
    1.31
    stalgia
    1.30
    ！"
    1.30
    nnnn
    1.27
    】：
    1.27
    SS
    1.27
    get
    1.25
    Activations Density 0.047%

    No Known Activations