© 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. 176267
    Prev
    Next
    INDEX
    Explanations

    transportation and visuals

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

    state, response, video, school, bleach

    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
    Negative Logits
     وتح
    0.47
     باستخدام
    0.46
     elektronic
    0.46
    𐱅
    0.44
     ecuación
    0.43
     equilíbrio
    0.43
    咨询
    0.42
    俭
    0.42
    ِن
    0.40
     historischen
    0.40
    POSITIVE LOGITS
    દાર
    0.46
     Fract
    0.45
     respectiv
    0.44
    _{
    0.44
    )=
    0.43
    рома
    0.43
    дра
    0.42
     fract
    0.42
     Drawable
    0.42
     calci
    0.42
    Activations Density 0.001%

    No Known Activations