© 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. 204838
    Prev
    Next
    INDEX
    Explanations

    apply, irrational, think, house, variable, separate, details

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

    18th century phrasing

    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
    The
    0.45
     curb
    0.44
    V
    0.44
    αν
    0.43
    Green
    0.43
    ק
    0.42
    पुर
    0.41
    Drag
    0.41
     그런
    0.41
    That
    0.41
    POSITIVE LOGITS
     Neuros
    0.52
     Translational
    0.50
     pelayanan
    0.49
     Berechnung
    0.49
     Deutschen
    0.49
     Physiology
    0.48
     sécrétion
    0.48
     Бүген
    0.48
     alimentação
    0.47
    摖
    0.47
    Activations Density 0.000%

    No Known Activations