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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85810
    Prev
    Next
    INDEX
    Explanations

    dates and specific numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     jų
    -1.80
     mereka
    -1.78
     jejich
    -1.76
     onları
    -1.73
     esistono
    -1.63
    皷
    -1.62
     veilig
    -1.61
     estrena
    -1.59
    が無い
    -1.57
     bilgisayar
    -1.55
    POSITIVE LOGITS
     our
    2.11
     with
    1.98
     we
    1.78
     his
    1.67
     I
    1.65
     We
    1.58
     her
    1.53
     others
    1.50
     your
    1.45
     You
    1.43
    Activations Density 0.007%

    No Known Activations