© 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. 74007
    Prev
    Next
    INDEX
    Explanations

    lists with commas and conjunctions

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

    Lua monkeys jump spectrum

    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
    teryx
    0.52
    షా
    0.51
    内置
    0.49
    廈
    0.48
    n
    0.48
    atação
    0.46
     leitura
    0.46
    戒指
    0.45
    akaian
    0.45
     निजा
    0.45
    POSITIVE LOGITS
    ENE
    0.48
     fod
    0.45
     거기에
    0.44
    ぜ
    0.44
     స్టే
    0.44
     manned
    0.43
     fistule
    0.43
     CIN
    0.43
     imagination
    0.42
     결
    0.42
    Activations Density 0.001%

    No Known Activations