© 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. 172867
    Prev
    Next
    INDEX
    Explanations

    programming documentation fields metrics

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

    documentation comments in code

    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
    ⵄ
    0.83
     développ
    0.63
    ᕇ
    0.63
    6
    0.63
    م
    0.60
    3
    0.58
    тан
    0.57
    یی
    0.57
    м
    0.57
    هم
    0.57
    POSITIVE LOGITS
    ↵
    0.93
     in
    0.93
    '");
    0.68
     {
    0.59
     illegal
    0.57
     %)
    0.57
     請
    0.56
    </h2>
    0.56
    在
    0.56
     currentPage
    0.55
    Activations Density 0.000%

    No Known Activations