© 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-262K
    7. 220225
    Prev
    Next
    INDEX
    Explanations

    blaming, fully remote, contains, point

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Src
    0.48
     dedos
    0.44
    訌
    0.42
     shooting
    0.41
    駛
    0.41
     shootings
    0.41
     ৮০
    0.41
     spell
    0.40
     proceeding
    0.40
     fingerprint
    0.40
    POSITIVE LOGITS
    ":[{"
    0.42
    GAN
    0.41
    oxet
    0.38
    lomer
    0.38
    extractor
    0.38
    Invariant
    0.37
     Feldman
    0.37
     nær
    0.36
     Tian
    0.35
    laut
    0.35
    Activations Density 0.000%

    No Known Activations