© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86284
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    '
    -2.27
    there
    -1.93
     While
    -1.90
    钲
    -1.80
     while
    -1.73
    也
    -1.72
     vostra
    -1.70
     necessary
    -1.67
     singola
    -1.67
     There
    -1.63
    POSITIVE LOGITS
    ArgsConstructor
    1.88
     doivent
    1.79
    TERY
    1.77
    jects
    1.76
    olate
    1.72
    鲀
    1.71
     głównie
    1.71
    ఽ
    1.70
    ☫
    1.70
    laria
    1.70
    Activations Density 0.000%

    No Known Activations