© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101775
    Prev
    Next
    INDEX
    Explanations

    Primary School or FROM your

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TOF
    0.41
    Unicode
    0.39
     선정
    0.39
     Yukawa
    0.38
     Underwood
    0.37
    ൨
    0.37
    Donald
    0.37
    ángulos
    0.36
    ノー
    0.36
    Per
    0.36
    POSITIVE LOGITS
    整備
    0.39
    บาท
    0.38
     оюн
    0.38
    🅷
    0.35
    IVIDUAL
    0.34
     behaviours
    0.33
    ทยาลัย
    0.33
     DispatchQueue
    0.33
    تاة
    0.33
     QApplication
    0.33
    Activations Density 0.000%

    No Known Activations