© 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. 135061
    Prev
    Next
    INDEX
    Explanations

    Shine tracks, my genealogical, has been, stunning color

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

    cryptids and trichomes

    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
    пы
    0.50
     लगभग
    0.47
    ponent
    0.46
    ^{'
    0.46
     \
    0.45
    dengan
    0.45
     पसंदीदा
    0.45
     dérivés
    0.43
    |^
    0.43
    Default
    0.43
    POSITIVE LOGITS
    感恩
    0.46
    ངས་
    0.46
     Mods
    0.44
     Alone
    0.43
    junctive
    0.43
    瑪
    0.43
    商業
    0.42
    对我
    0.42
    iqu
    0.42
    abis
    0.42
    Activations Density 0.001%

    No Known Activations