© 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. 235768
    Prev
    Next
    INDEX
    Explanations

    HYDRO BAN

    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
    ppings
    0.48
    ጭ
    0.47
    น
    0.46
     sofern
    0.44
    н
    0.44
     formality
    0.43
    ن
    0.43
     应
    0.42
    ;}
    0.42
    hensive
    0.42
    POSITIVE LOGITS
    িউ
    0.47
    کار
    0.47
     destacar
    0.46
    Zap
    0.46
     olvidar
    0.46
     julho
    0.46
     guarda
    0.46
    هاي
    0.45
    کری
    0.44
     cento
    0.43
    Activations Density 0.001%

    No Known Activations