© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 66323
    Prev
    Next
    INDEX
    Explanations

    engineering and selections

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

    abstract concepts and methods

    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
    흉
    0.47
    숨
    0.47
    ীকে
    0.46
    িশালী
    0.46
    менить
    0.46
    緊急
    0.46
    furter
    0.45
     स्तर
    0.45
    рона
    0.44
    крыть
    0.43
    POSITIVE LOGITS
     mantras
    0.50
     deliberations
    0.47
     Engineering
    0.47
    选择
    0.46
    ’
    0.46
     选择
    0.46
     engineering
    0.46
     ইহা
    0.46
     dealings
    0.45
     Agriculture
    0.43
    Activations Density 0.000%

    No Known Activations