© 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. 16727
    Prev
    Next
    INDEX
    Explanations

    java file paths

    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
    Negative Logits
     if
    -1.25
     begins
    -1.24
     (
    -1.21
     even
    -1.16
     began
    -1.15
    !!!!!
    -1.14
     appears
    -1.14
    tamaan
    -1.12
     starts
    -1.11
     vermelhas
    -1.11
    POSITIVE LOGITS
     rassemb
    1.28
     quels
    1.23
     bijvoorbeeld
    1.19
    pentru
    1.18
     davvero
    1.18
     rése
    1.17
     empê
    1.17
     molte
    1.16
     vergeten
    1.16
     quelles
    1.14
    Activations Density 0.001%

    No Known Activations