© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181990
    Prev
    Next
    INDEX
    Explanations

    costs and damages

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

    evoke certain, into electrical, ASCII art

    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
     胡
    0.59
     不是
    0.54
     오히려
    0.53
     杨
    0.52
     कपकेक
    0.49
     हू
    0.49
    ahuasca
    0.49
    IRY
    0.47
     朱
    0.47
     Bukan
    0.47
    POSITIVE LOGITS
    Servo
    0.40
     digital
    0.40
    Digital
    0.39
    楽天
    0.39
    ေ
    0.39
    Minist
    0.38
     finanz
    0.38
    Place
    0.38
    Sports
    0.38
    zón
    0.37
    Activations Density 0.001%

    No Known Activations