© 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. 142617
    Prev
    Next
    INDEX
    Explanations

    generate, regenerate, serving

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

    describing website or app functionality

    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
    Negative Logits
    ulman
    0.44
    Ро
    0.42
    худ
    0.42
    瓈
    0.41
    Quer
    0.40
     endeavoured
    0.39
     ডিজাই
    0.39
    essoa
    0.38
    الان
    0.38
     ออก
    0.38
    POSITIVE LOGITS
     regener
    0.42
     regenerate
    0.40
     testis
    0.40
     regenerating
    0.40
     ¥
    0.40
    の見
    0.40
     জ
    0.39
     generate
    0.38
     firebase
    0.38
     pyrite
    0.38
    Activations Density 0.000%

    No Known Activations