© 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. 226830
    Prev
    Next
    INDEX
    Explanations

    legal roles and responsibilities

    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
    我
    0.57
    あ
    0.57
    К
    0.54
    자
    0.51
    爆
    0.51
    রহ
    0.50
    嘭
    0.49
    تباين
    0.49
    イ
    0.49
    沖縄
    0.48
    POSITIVE LOGITS
     الرابعه
    0.52
     लॉ
    0.48
     sexto
    0.48
     बैड
    0.47
     sixth
    0.46
     পড়ে
    0.46
     fifth
    0.44
     சென்று
    0.43
    icelli
    0.43
     seguro
    0.42
    Activations Density 0.000%

    No Known Activations