© 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. 94758
    Prev
    Next
    INDEX
    Explanations

    professional design

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

    foreign words

    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
     گزینه
    0.50
     دارای
    0.48
     matches
    0.47
    商品説明
    0.47
     ikut
    0.46
    ⤴
    0.46
    OPTIONS
    0.46
    符合
    0.45
    ("../../
    0.44
     viable
    0.44
    POSITIVE LOGITS
    änden
    0.44
    ರೆ
    0.43
     Schreiben
    0.43
    写的
    0.42
    örung
    0.41
    örungen
    0.40
    rary
    0.40
    ន្ទ
    0.40
    诗人
    0.40
     Фер
    0.39
    Activations Density 0.000%

    No Known Activations