© 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. 202126
    Prev
    Next
    INDEX
    Explanations

    two followed by number or unit

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

    technical descriptions and explanations

    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
    กรม
    0.48
    闇
    0.48
    BLUE
    0.48
     convection
    0.47
    斑
    0.47
    一
    0.47
     quite
    0.46
    음
    0.46
    XP
    0.46
     lily
    0.46
    POSITIVE LOGITS
     $"{
    0.48
     AcOH
    0.47
     mengembangkan
    0.47
     Selanjutnya
    0.46
     untuk
    0.45
     {...
    0.45
     Lihat
    0.45
     Isaac
    0.45
     <--
    0.44
    hend
    0.44
    Activations Density 0.001%

    No Known Activations