© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205153
    Prev
    Next
    INDEX
    Explanations

    sample

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts and their explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     eighty
    0.42
     eight
    0.42
     다섯
    0.42
     crumbling
    0.42
     쿠
    0.41
     affiliations
    0.41
     ninety
    0.40
    ทรัพย์
    0.40
    屽
    0.40
     अर्चना
    0.40
    POSITIVE LOGITS
    biid
    0.49
     continua
    0.44
     sporadically
    0.44
     polygons
    0.43
    steiger
    0.43
    រួម
    0.43
    alignParent
    0.42
    maty
    0.42
    rotic
    0.42
    एनएल
    0.41
    Activations Density 0.001%

    No Known Activations