© 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. 179794
    Prev
    Next
    INDEX
    Explanations

    curse of, little or

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

    common convention/technique

    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
    娌
    0.52
    ница
    0.50
    фесси
    0.50
     Акы
    0.49
    莽
    0.48
    ПК
    0.48
     Zert
    0.47
     Akademie
    0.47
    рида
    0.46
    АК
    0.46
    POSITIVE LOGITS
    de
    0.55
    *
    0.54
    ```
    0.51
    I
    0.51
    IC
    0.49
    eng
    0.49
    II
    0.49
     ，
    0.49
    Living
    0.49
    ot
    0.48
    Activations Density 0.000%

    No Known Activations