© 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-65K
    7. 55586
    Prev
    Next
    INDEX
    Explanations

    Parliament ament

    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_65k_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
    т
    0.57
    ت
    0.50
    💣
    0.49
    ट्रोल
    0.48
    บน
    0.47
    л
    0.45
     جی
    0.45
    ！
    0.45
    лл
    0.45
    ต
    0.45
    POSITIVE LOGITS
     phenomena
    0.51
     racemic
    0.48
     Strept
    0.45
     pathogenesis
    0.43
     migrants
    0.43
     Homo
    0.42
     meningitis
    0.41
     Creat
    0.41
     perempt
    0.41
     burials
    0.41
    Activations Density 0.013%

    No Known Activations