© 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-16K
    7. 12647
    Prev
    Next
    INDEX
    Explanations

    generative AI

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Chess
    0.43
     chess
    0.42
    Gent
    0.42
    濩
    0.40
     قرب
    0.39
    Chess
    0.39
    働
    0.39
     యు
    0.39
     Kuznet
    0.39
    chinen
    0.38
    POSITIVE LOGITS
     zipper
    0.40
     pInBuffer
    0.39
     аэро
    0.38
     detr
    0.36
     night
    0.36
    ahiya
    0.35
    Night
    0.35
    ہی
    0.35
    flower
    0.34
    flip
    0.34
    Activations Density 0.045%

    No Known Activations