© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3740
    Prev
    Next
    INDEX
    Explanations

    ISBNs and URLs

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     banned
    0.64
     are
    0.63
     speaker
    0.61
    ↵↵
    0.60
     video
    0.58
     Take
    0.57
     experience
    0.55
     topics
    0.53
    est
    0.52
    am
    0.52
    POSITIVE LOGITS
    دين
    0.58
     Egipto
    0.57
     丶
    0.55
    };\
    0.55
    тип
    0.55
    덬
    0.55
    OA
    0.54
    GJ
    0.54
    Ꭺ
    0.54
     EJ
    0.54
    Activations Density 0.002%

    No Known Activations