© 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. 124768
    Prev
    Next
    INDEX
    Explanations

    classical guitar, reverse engineering, local arrival

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

    beyond, chef, potentially, else, functions

    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
    changing
    0.50
    絘
    0.48
     deportivos
    0.48
     específicos
    0.47
     академи
    0.47
     académico
    0.46
    𝙥
    0.46
     rápidos
    0.46
     периоди
    0.46
     avión
    0.46
    POSITIVE LOGITS
    otong
    0.52
     reassurance
    0.45
     decar
    0.44
     litigants
    0.44
    備
    0.43
    ashmir
    0.43
    ;:
    0.42
    araman
    0.42
    rophy
    0.42
    reeting
    0.42
    Activations Density 0.001%

    No Known Activations