© 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. 240218
    Prev
    Next
    INDEX
    Explanations

    cars from, summer sky, One idea

    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
     bahan
    0.47
     ['
    0.46
     بڑ
    0.45
     sails
    0.44
     ["
    0.44
     echoes
    0.44
     cereals
    0.43
     ماضی
    0.43
     ->
    0.42
     dries
    0.42
    POSITIVE LOGITS
    the
    0.51
    ስቃ
    0.50
    оз
    0.48
     દરેક
    0.48
    m
    0.48
    bl
    0.46
     တော့
    0.46
    myst
    0.46
    峤
    0.45
    top
    0.45
    Activations Density 0.001%

    No Known Activations