© 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. 21619
    Prev
    Next
    INDEX
    Explanations

    recommendations for actions

    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
    tives
    -1.23
    _
    -1.21
    杙
    -1.19
    à
    -1.14
    ú
    -1.11
     onları
    -1.09
     The
    -1.08
     งาน
    -1.06
    差点
    -1.06
    parently
    -1.06
    POSITIVE LOGITS
     be
    1.38
    אָ
    1.38
     by
    1.31
     before
    1.29
    }$,
    1.27
     však
    1.27
    attu
    1.26
     azonban
    1.24
     koniecz
    1.21
     炖
    1.17
    Activations Density 0.085%

    No Known Activations