© 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-16K
    7. 12321
    Prev
    Next
    INDEX
    Explanations

    numbers 3, 5

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

    iteration with `range(`

    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_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
    acet
    0.50
    mlabeledtr
    0.44
     визуа
    0.43
    alc
    0.43
     手
    0.43
     每
    0.41
    ርዝ
    0.41
    উর
    0.40
     режиме
    0.40
    opt
    0.39
    POSITIVE LOGITS
     다섯
    0.47
     ثلاثة
    0.47
     tři
    0.46
     beş
    0.44
     ஐந்து
    0.43
    전에
    0.43
     čty
    0.42
    五个
    0.42
    三天
    0.42
     तीन
    0.42
    Activations Density 0.002%

    No Known Activations