© 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. 128363
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    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
     to
    -1.68
    }}
    -1.46
     chyba
    -1.33
    丁目
    -1.27
     Any
    -1.27
     What
    -1.22
    ()));
    -1.22
    %]
    -1.19
     decât
    -1.19
     his
    -1.16
    POSITIVE LOGITS
     of
    1.97
    伫
    1.30
    đèn
    1.30
    椟
    1.27
    榎
    1.26
    ჱ
    1.26
    bleiben
    1.25
    ◆◇
    1.25
    还会
    1.24
    你这
    1.24
    Activations Density 0.009%

    No Known Activations