© 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. 160023
    Prev
    Next
    INDEX
    Explanations

    general phrases and specific terms

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

    category, immobility, root, pencil, surface

    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
    sobre
    0.45
    ૩
    0.43
     getName
    0.42
    色は
    0.41
     celebró
    0.41
     बढ़ाया
    0.41
     actores
    0.40
     धनराशि
    0.40
    >→</
    0.39
    役割
    0.39
    POSITIVE LOGITS
     Immobil
    0.54
     Category
    0.49
    ีก
    0.46
     Fractal
    0.46
    ায়ক
    0.46
     eggplant
    0.46
     이것
    0.45
     ASP
    0.45
     asymptotically
    0.45
     FCM
    0.44
    Activations Density 0.003%

    No Known Activations