© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87284
    Prev
    Next
    INDEX
    Explanations

    cardiac arrhythmia

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

    anime girls, romance roleplay

    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
    Revel
    0.47
    靶
    0.45
    ﺼ
    0.44
    芪
    0.43
    gester
    0.41
     сожа
    0.41
    糙
    0.41
    CLion
    0.40
    Sunshine
    0.40
    Edwards
    0.40
    POSITIVE LOGITS
    ia
    0.51
     counc
    0.42
     ◎
    0.42
     precum
    0.42
     Kofi
    0.41
     भवन
    0.40
     המח
    0.40
     способ
    0.40
     ders
    0.40
     wearer
    0.40
    Activations Density 0.000%

    No Known Activations