© 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. 226700
    Prev
    Next
    INDEX
    Explanations

    proprietary technical terms

    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
    am
    0.54
    িতা
    0.49
    ang
    0.48
     H
    0.48
    ua
    0.47
     DOES
    0.47
     hound
    0.47
     Hound
    0.47
     Abia
    0.47
     Lear
    0.45
    POSITIVE LOGITS
    currentSprite
    0.52
    ꒪
    0.50
    곳
    0.49
     yılı
    0.47
    InstanceOf
    0.46
    diği
    0.46
    洄
    0.45
     multiplets
    0.45
    Телефон
    0.45
     الاسئله
    0.44
    Activations Density 0.000%

    No Known Activations