© 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. 44693
    Prev
    Next
    INDEX
    Explanations

    as is without warranty

    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
    RANGE
    0.41
    ښت
    0.41
    觞
    0.41
    ilikom
    0.41
     vocal
    0.40
     بە
    0.40
    ورس
    0.38
    UDN
    0.38
    颏
    0.38
    รวม
    0.38
    POSITIVE LOGITS
     без
    0.50
     वैसा
    0.47
    with
    0.46
     unfinished
    0.45
     no
    0.44
     without
    0.44
     Without
    0.44
     அப்படியே
    0.44
    ğı
    0.44
    fait
    0.43
    Activations Density 0.004%

    No Known Activations