© 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. 10-GEMMASCOPE-RES-131K
    7. 72322
    Prev
    Next
    INDEX
    Explanations

    physics and vector operations

    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_10/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
     raiſ
    -1.41
    termilk
    -1.41
     dinosaurio
    -1.38
    禤
    -1.38
     anſ
    -1.36
     anuncia
    -1.30
     dureza
    -1.30
     ネイル
    -1.30
     办
    -1.30
     deſt
    -1.30
    POSITIVE LOGITS
    0
    1.43
    8
    1.41
    </
    1.34
     altres
    1.30
    的所有
    1.30
    INA
    1.26
    ANG
    1.24
    relser
    1.20
     Können
    1.17
     लेकिन
    1.16
    Activations Density 0.014%

    No Known Activations