© 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. 25998
    Prev
    Next
    INDEX
    Explanations

    ih or ohr

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

    UHD Graphics, ATH, onload, UH, uth, FH

    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
    an
    1.05
    a
    0.89
    tól
    0.86
    િ
    0.83
    t
    0.83
    v
    0.83
    r
    0.79
    er
    0.79
    es
    0.74
    as
    0.73
    POSITIVE LOGITS
    ב
    1.13
    לו
    0.96
    אים
    0.80
    رح
    0.79
    ность
    0.79
    は
    0.78
    ми
    0.77
    เป็น
    0.75
    ره
    0.75
     crest
    0.74
    Activations Density 0.131%

    No Known Activations