© 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. 146787
    Prev
    Next
    INDEX
    Explanations

    manufacturing and services

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

    technical terms and structure

    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
    Desen
    0.48
    USSR
    0.47
     Един
    0.47
     alfabeto
    0.46
     vittoria
    0.44
    права
    0.44
     unico
    0.44
     조건
    0.43
    ಂಪ
    0.43
    낀
    0.43
    POSITIVE LOGITS
     πε
    0.46
    tolower
    0.43
    itudinal
    0.43
     u
    0.42
     ï
    0.41
    ï
    0.41
    z
    0.41
     boomerang
    0.41
     by
    0.40
     σε
    0.40
    Activations Density 0.001%

    No Known Activations