© 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. 128970
    Prev
    Next
    INDEX
    Explanations

    toward or towards

    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
    結果は
    -2.38
    !’
    -2.00
    特長
    -1.95
    方法は
    -1.94
    偌
    -1.91
    各样的
    -1.90
    ”。
    -1.88
     timed
    -1.80
     aña
    -1.79
    〠
    -1.77
    POSITIVE LOGITS
     They
    2.27
    他
    2.14
     THOSE
    1.95
     Atención
    1.91
    䊳
    1.90
    ，
    1.88
    это
    1.87
     Their
    1.81
    那些
    1.80
     infierno
    1.80
    Activations Density 0.015%

    No Known Activations