© 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. 39834
    Prev
    Next
    INDEX
    Explanations

    opinion

    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
    5
    -2.09
    6
    -1.93
    2
    -1.91
    1
    -1.73
    Einige
    -1.68
    3
    -1.64
    ulos
    -1.59
    7
    -1.57
    Zwischen
    -1.57
     بسبب
    -1.56
    POSITIVE LOGITS
    ,
    1.97
     It
    1.62
     on
    1.52
    projet
    1.48
     it
    1.46
    amigo
    1.45
     another
    1.45
     nowadays
    1.43
    expenses
    1.43
     their
    1.42
    Activations Density 0.001%

    No Known Activations