© 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. 80901
    Prev
    Next
    INDEX
    Explanations

    sight, innovations, second, monitor, types, unconscious, kingdom

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

    computing and technical descriptions

    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
     C
    0.47
    茜
    0.47
     rattled
    0.44
     nhằm
    0.44
     Manufacture
    0.44
    ys
    0.43
     MACH
    0.43
     elucidate
    0.43
     manufacture
    0.43
    osome
    0.42
    POSITIVE LOGITS
    ၅
    0.56
    rakt
    0.54
    Sister
    0.53
    religious
    0.50
    Orientation
    0.47
    percentage
    0.46
    $:
    0.46
    ර්ග
    0.46
    Lateral
    0.46
    Doll
    0.46
    Activations Density 0.001%

    No Known Activations