© 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. 124980
    Prev
    Next
    INDEX
    Explanations

    logos and looks

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

    class names or specific numbers

    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
    नॉ
    0.51
     CSV
    0.49
    <unused88>
    0.48
     똑
    0.48
    idot
    0.47
     செல்சியஸ்
    0.46
     कौनसा
    0.46
     kullanılan
    0.45
    挼
    0.45
    先前
    0.45
    POSITIVE LOGITS
     allied
    0.52
    _
    0.47
    faculty
    0.46
     alli
    0.46
     faculty
    0.45
     anticon
    0.45
     intersected
    0.44
    Pose
    0.44
     affords
    0.44
    пи
    0.42
    Activations Density 0.000%

    No Known Activations