© 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. 102680
    Prev
    Next
    INDEX
    Explanations

    ultimate determination, celebrating, tariffs, Ammonites

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

    Understanding the Goal & Tailoring

    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
    ↵↵
    0.52
    kah
    0.48
    ...
    0.46
    bar
    0.46
    vari
    0.45
    ?
    0.45
    kend
    0.45
    -
    0.45
    ogens
    0.45
     vem
    0.45
    POSITIVE LOGITS
    PLY
    0.50
    ਥ
    0.49
     quarterly
    0.48
    エット
    0.47
    AMSUNG
    0.46
     MACHIN
    0.45
    ೇಯ
    0.45
    ڠ
    0.45
     vouloir
    0.45
    ﻏ
    0.45
    Activations Density 0.000%

    No Known Activations