© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    compound nouns or collocations

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

    alternative names / aka

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

    parenthetical expressions

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    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
     ע
    0.43
    ിയാണ്
    0.42
     місто
    0.42
     тях
    0.41
    imamente
    0.41
    𝗣
    0.41
     مكتب
    0.40
    变革
    0.40
    řejmě
    0.40
     spineItem
    0.40
    POSITIVE LOGITS
     aka
    0.64
     AKA
    0.59
     yani
    0.57
    /
    0.43
     (
    0.40
     (=
    0.38
     অর্থাৎ
    0.38
    ;
    0.37
    <0xB6>
    0.36
    ings
    0.36
    Activations Density 0.384%

    No Known Activations