© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    quantifier followed by noun/adjective

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

    flood the channels

    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
     जबरदस्त
    0.48
    enna
    0.47
     बेहतरीन
    0.45
    www
    0.44
    ill
    0.43
    and
    0.43
    '
    0.43
    <0x80>
    0.41
     Хабаровского
    0.41
    still
    0.41
    POSITIVE LOGITS
    нням
    0.47
     vanes
    0.46
    স্পতি
    0.43
     humanidad
    0.43
     foundry
    0.42
     lecithin
    0.42
     acetylene
    0.42
     oxidase
    0.42
     acacia
    0.42
    वरणीय
    0.41
    Activations Density 0.000%

    No Known Activations