© 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. 74887
    Prev
    Next
    INDEX
    Explanations

    state abbreviations and locations

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

    stunning descriptions and dictionary definitions

    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
     scoreless
    0.50
    Ｏ
    0.46
    rtl
    0.46
    REFERENCE
    0.46
    RECORD
    0.45
    𝔪
    0.45
    StdHandle
    0.43
     مفه
    0.43
    ࣪
    0.43
    ###########
    0.43
    POSITIVE LOGITS
    зна
    0.50
    лью
    0.50
    ја
    0.48
     hạnh
    0.46
    шения
    0.46
     до
    0.45
    πτωση
    0.45
     sẽ
    0.45
     використання
    0.44
    га
    0.44
    Activations Density 0.001%

    No Known Activations