© 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. 101496
    Prev
    Next
    INDEX
    Explanations

    willing to verb

    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
     its
    -1.91
     The
    -1.88
    //
    -1.77
     will
    -1.72
     are
    -1.70
    c
    -1.65
    的高
    -1.63
    i
    -1.55
            
    -1.52
    For
    -1.52
    POSITIVE LOGITS
    脔
    2.23
    戋
    1.95
    ₶
    1.92
    雠
    1.70
    渐渐
    1.66
    composición
    1.66
    ⬈
    1.65
    趼
    1.63
    eavor
    1.63
    suggest
    1.62
    Activations Density 0.006%

    No Known Activations