© 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. 38368
    Prev
    Next
    INDEX
    Explanations

    this followed by punctuation

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

    as such

    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
    çi
    0.43
     egip
    0.42
    пред
    0.41
                     
    0.41
    برای
    0.39
     chứ
    0.38
    %。
    0.38
    但这
    0.38
    %.
    0.37
    สำหรับการ
    0.37
    POSITIVE LOGITS
     there
    0.63
    [,]
    0.58
     thì
    0.54
    ，
    0.54
    則
    0.53
     waxaa
    0.52
     maka
    0.48
    则
    0.47
    there
    0.46
    就要
    0.46
    Activations Density 0.058%

    No Known Activations