© 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. 65131
    Prev
    Next
    INDEX
    Explanations

    compound words

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

    proper nouns and technical terms

    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
     and
    0.54
    및
    0.47
     with
    0.46
     manos
    0.46
     for
    0.45
    ાઇ
    0.44
     و
    0.44
     in
    0.41
    وا
    0.39
     savo
    0.39
    POSITIVE LOGITS
    ™,
    0.41
     जिंदाबाद
    0.41
    體的
    0.39
    Longrightarrow
    0.37
     TextEditing
    0.37
     የሆነ
    0.37
    striatis
    0.37
    üsseldorf
    0.37
    ಲೆಂ
    0.37
    justify
    0.36
    Activations Density 0.143%

    No Known Activations