© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26136
    Prev
    Next
    INDEX
    Explanations

    label followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Blunt
    0.37
    rollees
    0.36
     negativ
    0.35
    ujo
    0.35
    Bapt
    0.35
     دف
    0.34
    よそ
    0.34
     illustrious
    0.34
     દર્
    0.34
    讴
    0.34
    POSITIVE LOGITS
     @
    0.41
     факторы
    0.40
    应用程序
    0.39
     Collar
    0.39
    気になる
    0.38
    :@
    0.38
     *@
    0.38
     एप्लिकेशन
    0.38
     অ্যাপ্লিকেশন
    0.37
     जर्नल
    0.37
    Activations Density 0.000%

    No Known Activations