© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11944
    Prev
    Next
    INDEX
    Explanations

    Wisconsin International Wade Roe

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric tokens (e.g. years, measurements, IDs) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     STEPS
    -0.93
     testi
    -0.88
    ᑕ
    -0.87
     ?-
    -0.86
     объяс
    -0.85
     technically
    -0.85
     encender
    -0.85
     OND
    -0.85
     ચ
    -0.82
     Sonos
    -0.82
    POSITIVE LOGITS
    cidade
    0.76
     lalu
    0.75
     Cel
    0.74
     Maybe
    0.73
     seems
    0.73
     for
    0.73
     prevent
    0.70
    嫣
    0.70
     over
    0.70
     fo
    0.70
    Activations Density 0.088%

    No Known Activations