© 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. 159555
    Prev
    Next
    INDEX
    Explanations

    click save or download

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

    data points, function, Wheeler, window, resignation

    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
    ه
    0.53
     inventions
    0.52
     Али
    0.52
     Produk
    0.52
     Sistem
    0.51
     neuen
    0.51
     Abdullah
    0.51
     Исто
    0.50
     Statistik
    0.49
     Pengembangan
    0.48
    POSITIVE LOGITS
    MinIntensity
    0.46
     ফিরিয়ে
    0.45
    ലുള്ള
    0.43
    grayscale
    0.43
    冀
    0.43
    为何
    0.42
    必須
    0.42
    modulo
    0.41
    岂
    0.41
    áték
    0.41
    Activations Density 0.000%

    No Known Activations