© 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. 195771
    Prev
    Next
    INDEX
    Explanations

    written permission

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

    authors of books

    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
    Basically
    0.53
    Happiness
    0.53
    Tampa
    0.50
    Isn
    0.50
    Birthday
    0.49
    গ
    0.49
    がら
    0.48
    IBM
    0.47
    centroids
    0.47
    Kitty
    0.46
    POSITIVE LOGITS
     elige
    0.54
     編
    0.49
     repost
    0.49
     Dispute
    0.49
     sal
    0.48
     memperbaiki
    0.47
     zaw
    0.46
     Newtonsoft
    0.46
     Us
    0.46
     oggi
    0.46
    Activations Density 0.000%

    No Known Activations