© 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. 237811
    Prev
    Next
    INDEX
    Explanations

    five adventure

    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
    亏
    0.46
    岔
    0.45
     نهاية
    0.44
     ولي
    0.43
     období
    0.42
    ليو
    0.42
     destabil
    0.42
    窜
    0.42
    码
    0.42
    投标文件
    0.41
    POSITIVE LOGITS
    one
    0.59
    propag
    0.51
    P
    0.49
    K
    0.49
     one
    0.48
    colour
    0.48
    calibration
    0.48
     standardization
    0.48
     decontamination
    0.47
    BR
    0.47
    Activations Density 0.000%

    No Known Activations