© 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. 135326
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific nouns

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

    Dark Humor, renal failure, enzymatic cleaners

    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
     ゴ
    0.48
    r
    0.47
     SYSTEM
    0.46
    SYSTEM
    0.45
    jske
    0.45
     متاب
    0.45
    사업
    0.44
    ጵ
    0.44
    jskim
    0.43
     SEQU
    0.43
    POSITIVE LOGITS
     পাপ
    0.42
     ordinaire
    0.41
    renner
    0.41
     bekannt
    0.40
     पाप
    0.40
    Exponential
    0.40
    odie
    0.39
    utzen
    0.39
     and
    0.39
    oud
    0.39
    Activations Density 0.000%

    No Known Activations