© 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. 61134
    Prev
    Next
    INDEX
    Explanations

    list, mapping, or transaction information

    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
     SCGS
    0.46
    X
    0.44
    in
    0.44
     ANOVA
    0.43
     Advisory
    0.43
     Время
    0.43
     JSC
    0.42
     জানিয়েছিলেন
    0.42
    taining
    0.40
     xếp
    0.40
    POSITIVE LOGITS
    Botan
    0.41
     numero
    0.41
     palladium
    0.40
     поли
    0.39
     benefic
    0.39
     decad
    0.38
     numeri
    0.38
    Ӏ
    0.38
     hehe
    0.38
     прости
    0.38
    Activations Density 0.026%

    No Known Activations