© 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. 25860
    Prev
    Next
    INDEX
    Explanations

    on feast, full, sacrifices

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

    a bit of

    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
    ς
    0.48
    OBJECT
    0.47
    łącznie
    0.46
    큽
    0.46
    ៨
    0.45
    𝟮
    0.44
    ों
    0.43
    χαν
    0.42
    ൨
    0.42
    Universität
    0.42
    POSITIVE LOGITS
     in
    0.67
    ,
    0.63
     is
    0.49
     of
    0.49
     will
    0.48
     verdens
    0.46
     or
    0.45
     ik
    0.45
    ing
    0.44
     o
    0.44
    Activations Density 0.283%

    No Known Activations