© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    more about, edited by, courtesy of

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

    recipe timings

    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
     from
    0.48
     от
    0.44
     awaits
    0.43
     with
    0.42
     greets
    0.41
     leucine
    0.41
    ，
    0.40
    goers
    0.40
    ,
    0.39
     από
    0.39
    POSITIVE LOGITS
     Untersuch
    0.48
    踌
    0.46
    スタル
    0.45
     vostre
    0.45
    licas
    0.44
     liberté
    0.44
    둴
    0.42
    وزیشن
    0.41
    پے
    0.40
    وامی
    0.39
    Activations Density 0.008%

    No Known Activations