© 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. 45644
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    Negative Logits
     Already
    -1.41
    jeu
    -1.38
    鍮
    -1.38
    avajillas
    -1.38
     ſeveral
    -1.36
     anello
    -1.34
     seperti
    -1.30
    ДР
    -1.30
    Харак
    -1.30
    negara
    -1.30
    POSITIVE LOGITS
     who
    1.52
    </i>
    1.52
     if
    1.48
     
    1.38
    </em>
    1.37
     barely
    1.29
     those
    1.26
     Fähigkeit
    1.25
     whose
    1.24
     whom
    1.24
    Activations Density 0.025%

    No Known Activations