© 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. 165090
    Prev
    Next
    INDEX
    Explanations

    symbols before specific terms

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

    math notation and code

    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
    чий
    0.45
    inald
    0.44
    芭
    0.43
    嗚
    0.43
    旗下
    0.42
     ухуд
    0.42
    ashima
    0.41
     ガ
    0.40
     Gar
    0.39
    вших
    0.39
    POSITIVE LOGITS
     translational
    0.47
     eigenvalues
    0.45
     unary
    0.41
     therapeut
    0.40
     renormalized
    0.40
     linkages
    0.39
     geographically
    0.39
     morphological
    0.38
     mutate
    0.38
     neurons
    0.38
    Activations Density 0.001%

    No Known Activations