© 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. 4935
    Prev
    Next
    INDEX
    Explanations

    titles followed by prepositions

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

    book introductions and history sections

    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
    :‏
    0.43
    ：《
    0.42
     Übersicht
    0.42
    ಃ
    0.41
    ："
    0.40
    ：“
    0.40
    ઃ
    0.40
    ：
    0.39
    ():
    0.38
    __:
    0.38
    POSITIVE LOGITS
     for
    0.49
     from
    0.40
    Ã
    0.39
     nejen
    0.38
     [&
    0.37
    Â
    0.37
    jeva
    0.36
     in
    0.35
    ŝ
    0.35
     with
    0.35
    Activations Density 0.027%

    No Known Activations