© 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. 4939
    Prev
    Next
    INDEX
    Explanations

    figure labels and descriptions

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

    images and diagrams

    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
     propriétaires
    0.69
     réforme
    0.68
     auraient
    0.64
     pewno
    0.64
    <unused47>
    0.63
     asuntos
    0.63
     jornalista
    0.63
    acariy
    0.63
    частли
    0.62
    ພວກ
    0.61
    POSITIVE LOGITS
     Figure
    0.97
     Fig
    0.95
     diagram
    0.92
     schematic
    0.91
    示意
    0.88
    Fig
    0.87
     Schematic
    0.85
    A
    0.84
     showing
    0.83
     micrograph
    0.83
    Activations Density 0.150%

    No Known Activations