© 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. 135125
    Prev
    Next
    INDEX
    Explanations

    if someone could

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

    new information and comparisons

    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
     ક્ષ
    0.56
     númer
    0.55
     formulario
    0.54
     ժ
    0.53
     Estadística
    0.53
     Empresas
    0.52
     Matemática
    0.52
     ფორ
    0.51
    ટ્સ
    0.51
     точке
    0.50
    POSITIVE LOGITS
     secretion
    0.52
    -
    0.51
     production
    0.50
     secretions
    0.50
     juice
    0.49
     regulating
    0.46
     boilers
    0.44
     systems
    0.43
     colored
    0.43
     chutes
    0.43
    Activations Density 0.000%

    No Known Activations