© 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. 81368
    Prev
    Next
    INDEX
    Explanations

    languages, institute, market

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

    bias, discrimination, attack

    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
    in
    0.52
    l
    0.49
    lad
    0.47
     n
    0.47
    able
    0.46
    split
    0.45
    S
    0.45
    und
    0.44
    ת
    0.44
    '-
    0.43
    POSITIVE LOGITS
     அமைந்துள்ள
    0.54
     测试
    0.52
    ктери
    0.52
     Scanning
    0.52
    وانی
    0.51
    اهای
    0.50
    akkhati
    0.49
    原始内容存档
    0.49
    ಾಯಿತು
    0.48
     अंजाम
    0.48
    Activations Density 0.002%

    No Known Activations