© 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. 11290
    Prev
    Next
    INDEX
    Explanations

    principal and formulas

    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
    釭
    0.44
    }^{+}$.
    0.43
    秙
    0.42
    茥
    0.42
     Regl
    0.41
     मेथड
    0.41
    .).
    0.40
     المسافه
    0.40
    稃
    0.40
    香味
    0.40
    POSITIVE LOGITS
     AUTHORS
    0.41
     Sequelize
    0.40
    超出
    0.39
     ujarnya
    0.38
     maupun
    0.37
     அவருடைய
    0.36
     defies
    0.36
     authored
    0.36
    从小
    0.36
    COPY
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.