© 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. 187779
    Prev
    Next
    INDEX
    Explanations

    prepositions or auxiliary verbs

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

    Hello world, principles, contains, make

    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
    id
    0.53
     Saratoga
    0.50
     fists
    0.50
     MLS
    0.49
    u
    0.49
     \%
    0.49
     Shiraz
    0.49
    ut
    0.48
     inaugur
    0.48
     Malibu
    0.48
    POSITIVE LOGITS
    Comparison
    0.50
    ందిన
    0.50
     grafico
    0.49
    Kom
    0.46
    Dell
    0.46
     angew
    0.45
    Graf
    0.45
    Coder
    0.45
    ంప
    0.44
    鄱
    0.44
    Activations Density 0.000%

    No Known Activations