© 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. 62518
    Prev
    Next
    INDEX
    Explanations

    legal notices and disclaimers

    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
     BLOCK
    -0.84
     conifers
    -0.78
     冬
    -0.75
    ∵
    -0.73
     süt
    -0.73
     nerv
    -0.73
    Кра
    -0.72
    BLOCK
    -0.71
     Drago
    -0.71
     optima
    -0.71
    POSITIVE LOGITS
     Annual
    0.90
     annual
    0.90
     pledged
    0.86
     revenue
    0.85
     rental
    0.80
     Senior
    0.78
     yearly
    0.78
     tests
    0.78
     Additional
    0.77
     senior
    0.77
    Activations Density 0.006%

    No Known Activations