© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123743
    Prev
    Next
    INDEX
    Explanations

    npmjs, showthread links

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

    the word "unused" in programming code contexts (variable names, compiler flags, and comments).

    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
     bekämp
    -2.23
     kämp
    -2.06
     It
    -1.92
     Inſ
    -1.92
    などと
    -1.91
     Conſ
    -1.91
    拥抱
    -1.85
     werfen
    -1.83
    じゃなくて
    -1.83
    個人的
    -1.83
    POSITIVE LOGITS
    d
    2.42
    ،
    2.06
    д
    1.99
    鴣
    1.97
    y
    1.97
    \
    1.91
    b
    1.89
    the
    1.88
    re
    1.82
    ll
    1.82
    Activations Density 0.001%

    No Known Activations