© 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. 219840
    Prev
    Next
    INDEX
    Explanations

    artists, car, or mail

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

    Illustrating hypothetical or specific scenarios

    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
     spowod
    0.50
     uygulama
    0.50
     организм
    0.50
    魈
    0.50
    𓏧
    0.50
     тенден
    0.50
    என்ன
    0.49
     причины
    0.48
     sürec
    0.48
     préférable
    0.47
    POSITIVE LOGITS
    acute
    0.47
     filling
    0.46
    add
    0.44
    ashing
    0.44
    filling
    0.44
    2
    0.43
    ar
    0.43
    Ž
    0.43
    ployee
    0.42
    att
    0.42
    Activations Density 0.003%

    No Known Activations