© 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. 182368
    Prev
    Next
    INDEX
    Explanations

    facility, years, developer

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

    domain name

    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
     Con
    0.44
     Pic
    0.43
    -
    0.41
    が終わ
    0.41
     C
    0.40
     K
    0.40
    н
    0.39
     Bov
    0.39
     Сара
    0.39
    뿡
    0.39
    POSITIVE LOGITS
    怸
    0.47
     eseguire
    0.47
    companions
    0.44
    ಲಯ
    0.43
    polish
    0.43
     හොඳ
    0.42
     været
    0.42
     প্রবেশ
    0.42
    晛
    0.42
     箱
    0.41
    Activations Density 0.002%

    No Known Activations