© 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. 44212
    Prev
    Next
    INDEX
    Explanations

    completed 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
    葙
    -1.98
    佧
    -1.81
    ،
    -1.80
    臜
    -1.71
    🢒
    -1.68
    という
    -1.63
    ges
    -1.62
    賔
    -1.62
    觧
    -1.59
    釭
    -1.59
    POSITIVE LOGITS
    正如
    1.48
     add
    1.38
    terea
    1.37
     incorporate
    1.36
    };*/
    1.35
    ↵
    1.35
    aimana
    1.34
    triques
    1.34
     as
    1.31
     Einwilligung
    1.31
    Activations Density 0.073%

    No Known Activations