© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81920
    Prev
    Next
    INDEX
    Explanations

    Accessibility, prerequisites, data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     कर्ज
    0.47
    trying
    0.47
     runtime
    0.46
     फक्त
    0.43
    찐
    0.43
    otoxic
    0.43
    really
    0.42
     rainy
    0.41
    toluene
    0.41
    𝓪
    0.41
    POSITIVE LOGITS
     Prerequisites
    0.45
     affords
    0.43
     ακό
    0.42
    acées
    0.42
     ഏറെ
    0.41
     Accessibility
    0.40
     consequently
    0.40
    ocèle
    0.40
     généralement
    0.39
     ছন্দ
    0.39
    Activations Density 0.020%

    No Known Activations