© 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. 227624
    Prev
    Next
    INDEX
    Explanations

    exclamations and announcements

    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
    *;
    0.52
     みんな
    0.50
     移動
    0.49
     系列
    0.48
     رئيس
    0.48
    といえば
    0.48
    ("../../
    0.47
    ユーザ
    0.47
     Mikolai
    0.47
     ڈ
    0.47
    POSITIVE LOGITS
     Muscles
    0.50
    迳
    0.48
    க்
    0.45
     urgent
    0.44
     Kenyan
    0.44
     Symptoms
    0.44
    দেশিক
    0.44
     muscles
    0.43
     exige
    0.43
     Za
    0.43
    Activations Density 0.005%

    No Known Activations