© 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-262K
    7. 80940
    Prev
    Next
    INDEX
    Explanations

    quantifying activities and finance

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Jurassic
    0.46
    Ext
    0.46
    建造
    0.44
    A
    0.43
     hered
    0.43
    Long
    0.42
    Saw
    0.42
    夏
    0.42
    六
    0.41
    ستان
    0.41
    POSITIVE LOGITS
    ujud
    0.51
     affixed
    0.48
     Liye
    0.46
     hinsichtlich
    0.45
     articolo
    0.44
     ಯಾವ
    0.44
    selling
    0.44
     informações
    0.44
     Tshirt
    0.43
    jgl
    0.43
    Activations Density 0.007%

    No Known Activations