© 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. 34-GEMMASCOPE-RES-131K
    7. 56791
    Prev
    Next
    INDEX
    Explanations

    number of counts

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    assemblée
    -0.73
     Hahaha
    -0.73
     noteworthy
    -0.70
     Haha
    -0.69
     schauen
    -0.69
     unless
    -0.69
     analgesic
    -0.67
     literate
    -0.66
     striving
    -0.65
     semilla
    -0.65
    POSITIVE LOGITS
     count
    3.63
     counts
    3.58
    count
    3.03
     Count
    2.89
     Counts
    2.81
    Count
    2.72
    counts
    2.69
    COUNT
    2.50
    Counts
    2.44
     COUNT
    2.42
    Activations Density 0.040%

    No Known Activations