© 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. 34924
    Prev
    Next
    INDEX
    Explanations

    biography and historical events

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

    manifest file

    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
     medicamentos
    0.50
    дея
    0.47
    嶷
    0.45
    ADER
    0.45
     интенсив
    0.45
    гиз
    0.44
    REEN
    0.44
     inteligentes
    0.44
    跛
    0.44
     গড়
    0.43
    POSITIVE LOGITS
     ব্রিগে
    0.45
     स्व
    0.44
    []>
    0.44
    ütt
    0.44
     collim
    0.44
     drawer
    0.42
     shortcut
    0.42
     violin
    0.41
     Hälfte
    0.41
    nrow
    0.40
    Activations Density 0.000%

    No Known Activations