© 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. 112040
    Prev
    Next
    INDEX
    Explanations

    computer, tool, Convention, method

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

    high, medium, or low

    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
    ्रो
    0.46
     exert
    0.45
     ಇಲ್ಲ
    0.45
    ो
    0.45
    യിലേ
    0.45
    ai
    0.44
     左
    0.44
    ്ര
    0.43
    owego
    0.43
     cutlery
    0.43
    POSITIVE LOGITS
    طفال
    0.45
    administered
    0.44
    無論
    0.43
    দয়
    0.41
    よく
    0.41
    مد
    0.40
    гласно
    0.40
    歩
    0.40
     COMPUTER
    0.40
    computer
    0.40
    Activations Density 0.000%

    No Known Activations