© 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. 202708
    Prev
    Next
    INDEX
    Explanations

    concept, them, facility, activities

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

    the most damaging scenarios

    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
    積極
    0.46
    祠
    0.45
     (
    0.43
    텍
    0.42
    gt
    0.42
    erce
    0.42
    れる
    0.41
    賴
    0.41
    墮
    0.41
    辩
    0.41
    POSITIVE LOGITS
    SanPham
    0.50
    elä
    0.48
    azienda
    0.47
    jelen
    0.47
    hingga
    0.46
    kében
    0.46
    nya
    0.45
    ênh
    0.44
     HUOBI
    0.44
     Función
    0.43
    Activations Density 0.001%

    No Known Activations