© 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. 53-GEMMASCOPE-2-RES-262K
    7. 78704
    Prev
    Next
    INDEX
    Explanations

    Hitler, Saudi, wellness, strength, before and after

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     тра
    0.45
     размеры
    0.41
    urbation
    0.41
    .$;
    0.40
    饪
    0.40
    ickej
    0.39
    telling
    0.39
     Dene
    0.38
    तर
    0.38
     dimens
    0.38
    POSITIVE LOGITS
     delicate
    0.42
     elegantly
    0.40
     yeri
    0.40
     váš
    0.40
    ố
    0.39
     ڈاک
    0.39
     blush
    0.38
     Deluxe
    0.38
     délic
    0.38
     Sexy
    0.38
    Activations Density 0.000%

    No Known Activations