© 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. 47371
    Prev
    Next
    INDEX
    Explanations

    defined layers, flash cards

    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
    a
    0.42
     pats
    0.42
     STATISTICS
    0.41
     Statistic
    0.41
    |
    0.41
     cok
    0.41
     _{
    0.40
    biggr
    0.40
    i
    0.40
    sr
    0.39
    POSITIVE LOGITS
     teknoloj
    0.57
     tecnologías
    0.56
    开发
    0.55
    ReactNative
    0.55
     రూపొ
    0.55
     technologie
    0.54
    Fullscreen
    0.54
    创新
    0.54
     платфор
    0.52
     SwiftUI
    0.52
    Activations Density 0.001%

    No Known Activations