© 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. 114202
    Prev
    Next
    INDEX
    Explanations

    jacketed

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

    actions that express belief

    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
    ら
    0.47
    รร
    0.43
    ліз
    0.43
    pidos
    0.43
    Grpc
    0.43
    ੇ
    0.42
    ів
    0.42
    ぴ
    0.42
    Укра
    0.42
    พิ
    0.42
    POSITIVE LOGITS
    )").
    0.47
     voed
    0.46
     chauffage
    0.46
     dùng
    0.45
    计量
    0.45
     Formula
    0.45
    အစိတ်အပိုင်း
    0.44
     Urb
    0.44
     flange
    0.44
    htub
    0.44
    Activations Density 0.002%

    No Known Activations