© 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. 44858
    Prev
    Next
    INDEX
    Explanations

    show signals or zones

    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
     conceptions
    0.45
    攬
    0.44
     sínt
    0.43
     élarg
    0.42
    সমূহ
    0.41
    ڑک
    0.39
     możli
    0.39
     preced
    0.39
    واصل
    0.38
    mobility
    0.38
    POSITIVE LOGITS
    0
    0.55
     Archivlink
    0.49
     जिससे
    0.46
     moisturizer
    0.46
    కు
    0.45
     clearInterval
    0.44
     через
    0.44
     florida
    0.42
     isEqualToString
    0.42
    ">-
    0.42
    Activations Density 0.000%

    No Known Activations