© 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. 219762
    Prev
    Next
    INDEX
    Explanations

    global innovation ecosystem

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

    words and code snippets

    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
    álu
    0.52
     Lugo
    0.46
     层
    0.44
     الطب
    0.43
    ceral
    0.43
     Mushroom
    0.43
     Será
    0.43
     tiro
    0.42
    áll
    0.42
    層
    0.41
    POSITIVE LOGITS
    渇
    0.46
    ]_{
    0.42
     बच्चे
    0.42
    \|=
    0.41
    wość
    0.41
    ブログ
    0.40
    Giving
    0.40
    े
    0.40
    우
    0.40
    วั
    0.40
    Activations Density 0.001%

    No Known Activations