© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150015
    Prev
    Next
    INDEX
    Explanations

    Andalusia Community, weekly show, logo, AL, your house

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

    parameters (7B, 13B, 70B)

    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
    Negative Logits
    面
    0.53
     pouvaient
    0.51
     Владимир
    0.49
    رق
    0.48
     contenders
    0.47
     quotas
    0.46
    ي
    0.46
     Владимира
    0.46
     ভুট্টোর
    0.46
    ի
    0.46
    POSITIVE LOGITS
     DO
    0.53
     Del
    0.49
    apa
    0.48
    <0x80>
    0.48
    ঁচ
    0.47
     UN
    0.47
     XO
    0.46
     hemat
    0.46
    ++)
    0.46
     HELP
    0.45
    Activations Density 0.002%

    No Known Activations