© 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. 238627
    Prev
    Next
    INDEX
    Explanations

    return, mission, extensions

    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
    ス
    0.52
    スティ
    0.51
    OrCreate
    0.50
    ヴィ
    0.49
    ヴァ
    0.49
    eo
    0.49
    ド
    0.48
    ト
    0.48
    rio
    0.48
    fm
    0.48
    POSITIVE LOGITS
     নিয়োগ
    0.46
     csal
    0.45
     Architektur
    0.44
    ärsk
    0.43
     deletions
    0.43
     Архів
    0.42
    信息的
    0.42
     incompat
    0.42
     Astrophysical
    0.41
     பொருந்த
    0.40
    Activations Density 0.000%

    No Known Activations