© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61014
    Prev
    Next
    INDEX
    Explanations

    within a certain limit

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Country
    0.53
    കേ
    0.49
    שת
    0.45
    강
    0.45
     Jno
    0.45
    Teacher
    0.45
    NEEDED
    0.45
     partnerships
    0.44
     Lehrer
    0.44
    LOGGER
    0.43
    POSITIVE LOGITS
     (
    0.44
    aza
    0.44
    切换
    0.43
    ,”
    0.41
     Bronco
    0.41
     evacuated
    0.41
     Napa
    0.41
     Diablo
    0.40
    减
    0.40
     అధిక
    0.40
    Activations Density 0.002%

    No Known Activations