© 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. 186019
    Prev
    Next
    INDEX
    Explanations

    highest Tribute award

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

    script, magenta, Gemma, contract, passages

    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
     való
    0.47
    мыс
    0.46
    未來
    0.44
     العن
    0.44
    잡
    0.44
    識
    0.43
    キ
    0.42
    주고
    0.41
    ява
    0.41
    মাল
    0.41
    POSITIVE LOGITS
     иллюстра
    0.47
     बलों
    0.46
    奠
    0.46
     THEY
    0.45
    arrison
    0.45
     appunto
    0.44
     Даже
    0.43
     Институт
    0.43
     ۲۰۱
    0.43
     empieza
    0.43
    Activations Density 0.000%

    No Known Activations