© 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. 12607
    Prev
    Next
    INDEX
    Explanations

    uddhism

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

    factual or technical terms

    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
    apods
    0.44
    乚
    0.44
    記憶
    0.43
    ﹗
    0.42
     cavité
    0.42
     peritone
    0.42
     droplets
    0.41
    Lk
    0.41
    ），
    0.41
    ゙
    0.41
    POSITIVE LOGITS
     cuestiones
    0.48
     racism
    0.48
     상품
    0.48
     universidades
    0.47
     nuestros
    0.47
     actitudes
    0.46
     nuestra
    0.46
     nossos
    0.46
     nostre
    0.46
     Bulld
    0.44
    Activations Density 0.000%

    No Known Activations