© 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. 238564
    Prev
    Next
    INDEX
    Explanations

    huge amount

    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
     پایان
    0.46
    drav
    0.45
    cleanup
    0.44
    inflammatory
    0.44
    alloway
    0.43
    옻
    0.42
    🪵
    0.42
    Georgian
    0.42
    otions
    0.42
    ointments
    0.41
    POSITIVE LOGITS
    Size
    0.52
     Size
    0.49
     FTSE
    0.45
     identificado
    0.44
    ®
    0.44
     subjected
    0.43
     Verifica
    0.43
     Sizes
    0.42
    ;
    0.42
     conceptually
    0.42
    Activations Density 0.001%

    No Known Activations