© 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. 222016
    Prev
    Next
    INDEX
    Explanations

    Global Medical

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

    specific items and descriptions

    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
    </h3>
    0.54
    рое
    0.50
     الأعمال
    0.49
     انه
    0.48
     subsp
    0.47
     accrued
    0.47
    grund
    0.46
     أنه
    0.46
     руха
    0.46
     estructural
    0.46
    POSITIVE LOGITS
    闓
    0.48
    igis
    0.47
    iglia
    0.47
    ható
    0.46
    iyas
    0.46
    iał
    0.46
    yyati
    0.44
    nian
    0.44
    নান
    0.43
    ascape
    0.43
    Activations Density 0.000%

    No Known Activations