© 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. 25108
    Prev
    Next
    INDEX
    Explanations

    descriptions of services

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

    Norse mythology

    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
    继续
    0.45
     nhật
    0.45
    ζει
    0.44
    做
    0.43
    årt
    0.42
    切
    0.42
    设立
    0.42
    鬼
    0.42
    ات
    0.41
    潁
    0.41
    POSITIVE LOGITS
    ۔
    0.53
     बनाम
    0.51
    S
    0.49
    U
    0.49
    X
    0.48
    llllll
    0.47
    O
    0.47
    Q
    0.46
    GRE
    0.45
     Hesap
    0.45
    Activations Density 0.000%

    No Known Activations