© 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. 15368
    Prev
    Next
    INDEX
    Explanations

    configuration comments

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

    API function use

    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
    ’
    0.67
    ur
    0.66
    ol
    0.65
    อย่างไร
    0.64
    ation
    0.63
    ी
    0.61
    avgsalary
    0.61
    บา
    0.61
     halfCanvas
    0.60
    ค
    0.59
    POSITIVE LOGITS
    ...*/
    0.78
    ↵
    0.72
     Произ
    0.67
     Vý
    0.62
    ів
    0.60
     Commencez
    0.60
     Esses
    0.60
     Tamaño
    0.59
     Taille
    0.59
     Carrera
    0.59
    Activations Density 0.001%

    No Known Activations