© 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. 40-GEMMASCOPE-2-RES-65K
    7. 4361
    Prev
    Next
    INDEX
    Explanations

    lisp, python, and ai code

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ши
    0.43
    र्गन
    0.40
    शिलाजीत
    0.39
     ngân
    0.39
    ಶ್ವ
    0.38
     ná
    0.38
     expiresIn
    0.38
    Singolare
    0.37
    िक्शन
    0.37
    >-</
    0.37
    POSITIVE LOGITS
     '(
    0.66
     nil
    0.62
     Clo
    0.61
     NIL
    0.59
     predicate
    0.59
     Nil
    0.57
     GNU
    0.57
     cdr
    0.57
     macros
    0.56
    `(
    0.56
    Activations Density 0.126%

    No Known Activations