© 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. 10-GEMMASCOPE-RES-131K
    7. 39286
    Prev
    Next
    INDEX
    Explanations

    exclusive, mutually, disjoint, logical operations

    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
    蔔
    -1.73
     Apparently
    -1.69
     –
    -1.65
     Perhaps
    -1.63
     and
    -1.63
     Surprisingly
    -1.55
    aupun
    -1.51
     помощью
    -1.51
     Although
    -1.49
     approval
    -1.48
    POSITIVE LOGITS
    ים
    1.59
     perciò
    1.54
     transparencia
    1.54
    and
    1.53
     verändert
    1.52
     dunque
    1.52
     erneu
    1.52
     pertanto
    1.49
     Vielzahl
    1.48
     gammel
    1.48
    Activations Density 0.016%

    No Known Activations