© 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. 100183
    Prev
    Next
    INDEX
    Explanations

    def method

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

    defining functions

    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
    #######
    0.44
     remont
    0.44
    ה
    0.43
    ことができる
    0.42
     helpers
    0.41
     অভিষেক
    0.41
     يمكن
    0.39
    ig
    0.39
    an
    0.39
    но
    0.39
    POSITIVE LOGITS
     scoot
    0.47
    镛
    0.45
    set
    0.44
     设置
    0.43
     inputted
    0.42
    olese
    0.42
    iformis
    0.41
    埙
    0.41
    ူး
    0.41
    setPointSize
    0.40
    Activations Density 0.000%

    No Known Activations