© 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. 123493
    Prev
    Next
    INDEX
    Explanations

    foreign language markers

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

    streaming platform compatibility

    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
    8
    0.54
     CONN
    0.54
    ান্ড
    0.50
     probado
    0.46
     spurt
    0.45
    Brainz
    0.45
    4
    0.45
     bisschen
    0.45
     kép
    0.45
    el
    0.44
    POSITIVE LOGITS
    ጠር
    0.54
     መን
    0.47
     Перед
    0.45
     স্থানের
    0.45
     перед
    0.43
    バ
    0.43
     HTMLSc
    0.42
     ラウンド
    0.42
    姦
    0.42
     영상을
    0.42
    Activations Density 0.001%

    No Known Activations