© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14029
    Prev
    Next
    INDEX
    Explanations

    rights reserved MAR NIGHT Mama Watches How Kau

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

    purpose is

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

    hyphen

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
    (
    1.00
    de
    0.89
    h
    0.88
    ли
    0.88
    d
    0.87
     of
    0.82
    (($
    0.80
    nya
    0.78
    that
    0.77
    লে
    0.76
    POSITIVE LOGITS
    0.84
    ˏ
    0.76
     гэта
    0.71
    _-
    0.66
    ＞
    0.66
    らは
    0.64
    らす
    0.63
     यांना
    0.62
    ,
    0.62
    .-
    0.61
    Activations Density 0.361%

    No Known Activations