© 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. 168136
    Prev
    Next
    INDEX
    Explanations

    heme BL

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

    explaining underlying impulses or themes

    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
     형태
    0.51
    ibald
    0.45
    PointSize
    0.45
     Đồng
    0.44
    hibition
    0.44
     참
    0.44
    jillo
    0.44
    文件夹
    0.43
    ilación
    0.43
     ব্যথা
    0.42
    POSITIVE LOGITS
    REN
    0.48
    s
    0.48
    sns
    0.47
    INES
    0.46
    >
    0.45
    CRS
    0.45
    もう
    0.44
    \
    0.44
    .
    0.44
    gcd
    0.44
    Activations Density 0.002%

    No Known Activations