© 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. 53375
    Prev
    Next
    INDEX
    Explanations

    linked together

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

    well-formed parentheses

    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
    ர்
    0.44
    ඨ
    0.43
    Psalm
    0.42
    |</
    0.41
    <0xA2>
    0.41
    autoprefixer
    0.41
     Isa
    0.41
    yección
    0.40
     voet
    0.40
    ർ
    0.39
    POSITIVE LOGITS
    プリン
    0.48
    ES
    0.47
    CHAIN
    0.46
    ESO
    0.46
    수한
    0.45
    ｿ
    0.45
    пример
    0.45
     экономи
    0.45
    憚
    0.45
     Chain
    0.44
    Activations Density 0.000%

    No Known Activations