© 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. 243520
    Prev
    Next
    INDEX
    Explanations

    specialist items, job details, machine information

    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
    carrier
    0.58
     ”
    0.52
     निजामाच्या
    0.49
    carriers
    0.48
    iano
    0.48
    mesine
    0.47
    rates
    0.46
     nucleons
    0.46
     tremendous
    0.46
    foods
    0.46
    POSITIVE LOGITS
    与其他
    0.49
    特
    0.48
    낫
    0.48
    辅助
    0.44
    注意事项
    0.44
    效应
    0.43
    ⓝ
    0.43
     paginate
    0.42
    专
    0.42
    权威
    0.42
    Activations Density 0.003%

    No Known Activations