© 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. 9885
    Prev
    Next
    INDEX
    Explanations

    many details, activities, issues

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

    reduced support

    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
    Crash
    0.50
    Merged
    0.48
    ˢ
    0.48
     পুর্ব
    0.47
     ګرځنده
    0.47
     ฟัง
    0.46
     Crash
    0.46
    RequestMethod
    0.46
     সাধারন
    0.46
    OnFileChange
    0.46
    POSITIVE LOGITS
     at
    0.54
    記者
    0.52
    $\
    0.46
    都是
    0.45
     comte
    0.43
    o
    0.43
     estaban
    0.43
    ر
    0.42
     in
    0.42
     idade
    0.42
    Activations Density 0.000%

    No Known Activations