© 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-262K
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    I am / I'm followed by description

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     genutzt
    0.25
    ῃ
    0.25
    د
    0.23
    με
    0.23
    增长
    0.22
    Lors
    0.22
     usamos
    0.22
    偣
    0.22
    чется
    0.22
    通用
    0.22
    POSITIVE LOGITS
     struggling
    0.45
     willing
    0.43
     trying
    0.42
     unable
    0.42
     afraid
    0.41
     aware
    0.41
     pleased
    0.40
     interested
    0.38
     sorry
    0.38
     conducting
    0.37
    Activations Density 0.034%

    No Known Activations