© 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. 162047
    Prev
    Next
    INDEX
    Explanations

    recommendations and try

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

    foreign language texts

    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
    0
    0.51
    的全
    0.48
    的要求
    0.47
    的最
    0.46
     R
    0.44
    ž
    0.43
    <0x89>
    0.42
    وب
    0.42
    ARD
    0.41
     F
    0.41
    POSITIVE LOGITS
     Фонбет
    0.58
     estrange
    0.58
    ര്‍ട്ട്
    0.57
     testicule
    0.55
     titulada
    0.55
     desviación
    0.54
    ා
    0.54
    Игра
    0.53
     пот
    0.52
     repente
    0.52
    Activations Density 0.001%

    No Known Activations