© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178121
    Prev
    Next
    INDEX
    Explanations

    wear and clothing

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

    code, math, json

    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
    АК
    0.58
    ક્તિ
    0.52
    ದಾರ
    0.48
    ultimo
    0.47
     idioma
    0.47
    ብዙ
    0.47
    اوی
    0.46
    얌
    0.46
    والفقار
    0.45
     Zombies
    0.44
    POSITIVE LOGITS
    ta
    0.47
    ;
    0.46
    ti
    0.45
    ste
    0.44
    类型
    0.44
    type
    0.44
    <0x80>
    0.43
    rose
    0.43
    de
    0.42
    琼
    0.42
    Activations Density 0.000%

    No Known Activations