© 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. 60119
    Prev
    Next
    INDEX
    Explanations

    as per, as required, outbreak of

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

    community, culture, language, expression

    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
    ógica
    0.50
     Scol
    0.49
    ino
    0.47
    í
    0.47
    ía
    0.47
    ó
    0.43
     Kans
    0.43
    ý
    0.43
    ém
    0.42
     Dunlop
    0.42
    POSITIVE LOGITS
     topRight
    0.50
    INSERT
    0.48
    व्य
    0.45
     domande
    0.45
     عزی
    0.45
     drawRight
    0.44
     необходимых
    0.44
    개를
    0.43
    適切な
    0.43
     consonant
    0.43
    Activations Density 0.000%

    No Known Activations