© 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. 90357
    Prev
    Next
    INDEX
    Explanations

    source, state, size, small

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

    lists and instructions

    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
     nights
    0.46
     enem
    0.46
     incisions
    0.45
     Dtsch
    0.44
     saws
    0.44
    ἡ
    0.43
    Ph
    0.43
    தமிழ்
    0.42
     submenu
    0.42
     drunkenness
    0.42
    POSITIVE LOGITS
    <0x9D>
    0.49
    esModule
    0.47
    ásticos
    0.47
    ’;
    0.45
    运维
    0.45
     Activision
    0.45
    ný
    0.44
    ované
    0.44
     δυνα
    0.44
    ’,
    0.44
    Activations Density 0.001%

    No Known Activations