© 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. 72536
    Prev
    Next
    INDEX
    Explanations

    longest serving directors

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

    the

    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
    ﻴ
    0.54
     Ngọc
    0.47
     bandera
    0.46
     carré
    0.45
     reproducción
    0.45
     administración
    0.45
     الترم
    0.45
     publicación
    0.44
     প্রার্থনা
    0.44
     Geol
    0.43
    POSITIVE LOGITS
    ＞
    0.46
    ीट
    0.44
    一只
    0.44
    (´
    0.44
    ब्रु
    0.43
    bay
    0.43
    before
    0.43
    (*´
    0.42
    tuple
    0.42
    मनी
    0.41
    Activations Density 0.000%

    No Known Activations