© 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. 23945
    Prev
    Next
    INDEX
    Explanations

    game mechanics, programming, descriptions

    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
     .
    0.54
     九
    0.51
    1
    0.47
     Nova
    0.45
     eclipse
    0.44
     online
    0.44
     Girls
    0.44
     teenage
    0.44
     halb
    0.43
    カートリッジ
    0.43
    POSITIVE LOGITS
    Укупно
    0.47
    ཋ
    0.45
    ਈ
    0.45
     веществ
    0.43
    瘴
    0.43
     художника
    0.43
     разли
    0.42
     सबकी
    0.41
    USR
    0.41
     정의역
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.