© 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. 96093
    Prev
    Next
    INDEX
    Explanations

    foreign languages and technical terms

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

    aiming for a goal

    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
    拓展
    0.44
    ညီ
    0.43
    whitelist
    0.42
     Muslims
    0.41
    university
    0.41
    ᱗
    0.41
    yyum
    0.40
    一段
    0.40
    阙
    0.39
     governors
    0.39
    POSITIVE LOGITS
     fejl
    0.50
    нка
    0.49
     മത്സ
    0.46
     contaminate
    0.46
    柣
    0.46
     belast
    0.45
    лка
    0.45
    Susp
    0.44
    ICK
    0.44
     диамет
    0.44
    Activations Density 0.001%

    No Known Activations