© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92389
    Prev
    Next
    INDEX
    Explanations

    library, sheep, calculate, suggest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     לת
    0.53
     ಕ್ಷೇತ್ರ
    0.51
     വിഷ
    0.47
    <unused404>
    0.47
     griev
    0.47
     stimulants
    0.46
     проблем
    0.45
     philanthrop
    0.45
     нарушения
    0.45
    forderung
    0.45
    POSITIVE LOGITS
     Concrete
    0.49
    ..
    0.45
     Brands
    0.44
    all
    0.44
    с
    0.43
    ring
    0.42
     Notebook
    0.42
    Duplicate
    0.42
     Ever
    0.42
    ędzy
    0.42
    Activations Density 0.004%

    No Known Activations