© 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. 61518
    Prev
    Next
    INDEX
    Explanations

    dates, days, times, posting information

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

    fraud indicators, deployments, hens

    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
    可以说是
    0.44
     balcon
    0.44
    খ্যার
    0.43
     삼각형
    0.43
    ್ಯ
    0.42
    丅
    0.42
     sagittal
    0.42
     côté
    0.41
    ϻ
    0.41
    ግር
    0.41
    POSITIVE LOGITS
     (
    0.45
    relse
    0.45
    INK
    0.44
     nen
    0.43
    9
    0.43
    ritu
    0.41
    fis
    0.41
    चंद
    0.41
    cind
    0.41
    ke
    0.41
    Activations Density 0.000%

    No Known Activations