© 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. 40-GEMMASCOPE-2-RES-65K
    7. 56157
    Prev
    Next
    INDEX
    Explanations

    pytorch tensor creation

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     corrupt
    0.39
     Overflow
    0.38
     тело
    0.38
     Pretty
    0.37
    辜
    0.36
    overlaps
    0.36
     overflowing
    0.36
     overrun
    0.35
    UST
    0.35
     guilty
    0.35
    POSITIVE LOGITS
     Seit
    0.40
    移民
    0.38
     풀
    0.37
    FhirExtension
    0.36
    ijev
    0.36
    šķ
    0.36
    ଣ
    0.36
     hib
    0.36
     clustering
    0.36
     bun
    0.36
    Activations Density 0.001%

    No Known Activations