© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    '
    -1.88
     -
    -1.80
    end
    -1.72
    v
    -1.69
     only
    -1.69
     by
    -1.65
    S
    -1.63
    u
    -1.63
    ('
    -1.58
    Only
    -1.55
    POSITIVE LOGITS
     cukru
    1.49
     takich
    1.43
     considerazione
    1.38
    戗
    1.38
     innych
    1.36
    larınız
    1.34
    Bibliografie
    1.34
     bepaalde
    1.33
    Complaints
    1.33
     壁紙
    1.32
    Activations Density 0.020%

    No Known Activations