© 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. 38838
    Prev
    Next
    INDEX
    Explanations

    declarative programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    in
    -1.99
    by
    -1.81
    c
    -1.73
    when
    -1.66
    …”
    -1.62
    y
    -1.62
    ”)
    -1.59
    ”,
    -1.57
    at
    -1.55
    ?”
    -1.55
    POSITIVE LOGITS
    ῞
    1.59
     Soporte
    1.46
    
    1.45
     podrás
    1.41
    <bos>
    1.41
    quién
    1.39
    來
    1.32
     destacados
    1.31
    がいい
    1.30
     miejsca
    1.29
    Activations Density 0.010%

    No Known Activations