© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61374
    Prev
    Next
    INDEX
    Explanations

    counting, logging, and heuristics

    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
     microw
    0.43
     hamburgers
    0.40
    🏅
    0.39
    holder
    0.38
    ധിപ
    0.38
     $(\
    0.37
     puan
    0.37
    metry
    0.37
    ponent
    0.37
    ilor
    0.37
    POSITIVE LOGITS
    ун
    0.42
     जा
    0.42
    Ꮈ
    0.40
    ઉસ
    0.39
     הי
    0.38
     conversely
    0.38
     Collectively
    0.38
     technician
    0.38
    ూర్
    0.37
     bravely
    0.37
    Activations Density 0.003%

    No Known Activations