© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89805
    Prev
    Next
    INDEX
    Explanations

    NOT negations

    np_acts-logits-general · gemini-2.5-flash-lite

    expression, communication, rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    0.56
    ต
    0.50
     Push
    0.48
    I
    0.48
    UseVisualStyle
    0.46
     Prit
    0.46
    Push
    0.45
    是他
    0.45
    スティ
    0.44
     公
    0.44
    POSITIVE LOGITS
     muestras
    0.51
     blends
    0.49
    ốc
    0.47
     estuvo
    0.47
     estrategias
    0.46
     variado
    0.46
     monedas
    0.46
     expressões
    0.46
     palco
    0.46
     essas
    0.45
    Activations Density 0.001%

    No Known Activations