© 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. 104092
    Prev
    Next
    INDEX
    Explanations

    level, wave, set

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

    Hunter Biden investigations

    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
    空间
    0.53
    ဆောင်
    0.47
    逃
    0.46
    ቄ
    0.46
    幅
    0.46
    身边
    0.45
    财富
    0.45
    相应
    0.44
    随机
    0.44
    韫
    0.44
    POSITIVE LOGITS
    weiss
    0.56
    air
    0.55
    paris
    0.54
    word
    0.54
    lamp
    0.54
    liga
    0.53
    lagen
    0.52
    lak
    0.52
    link
    0.52
    esse
    0.52
    Activations Density 0.001%

    No Known Activations