© 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. 133610
    Prev
    Next
    INDEX
    Explanations

    Cinema screening, Bluetooth menu, World Expo

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

    git branch names and git commands

    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
     Step
    0.49
     Maps
    0.47
     Sow
    0.45
     cycling
    0.45
     ఎదు
    0.44
    Step
    0.44
     :=
    0.43
     lush
    0.43
     Cue
    0.43
     Sector
    0.43
    POSITIVE LOGITS
     acompañada
    0.54
    ну
    0.52
    必要があります
    0.47
     décider
    0.47
    <0xA0>
    0.47
     deberían
    0.47
    ні
    0.46
     élevés
    0.45
    мові
    0.45
     déc
    0.45
    Activations Density 0.000%

    No Known Activations