© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32915
    Prev
    Next
    INDEX
    Explanations

    university and college education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.62
     our
    -1.46
    ふと
    -1.32
     beeintr
    -1.23
    //
    -1.22
     vuol
    -1.21
    為に
    -1.21
     beteiligt
    -1.17
     -
    -1.16
     the
    -1.15
    POSITIVE LOGITS
     และ
    1.55
    がありますが
    1.43
     createSprite
    1.40
    aret
    1.34
     rapporter
    1.27
    ⚢
    1.25
     炖
    1.25
    erdings
    1.22
    '')
    1.21
    leine
    1.20
    Activations Density 0.066%

    No Known Activations