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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 530
    Prev
    Next
    INDEX
    Explanations

    providing something

    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
     pérd
    -1.97
     vokal
    -1.81
    ise
    -1.78
     altamente
    -1.78
    ó
    -1.72
    Ꮂ
    -1.70
    妧
    -1.66
    ia
    -1.66
    まぁ
    -1.63
     elegan
    -1.62
    POSITIVE LOGITS
     with
    1.98
     for
    1.93
     With
    1.92
     This
    1.89
     had
    1.83
     a
    1.83
     which
    1.73
     in
    1.70
     Some
    1.69
     provide
    1.67
    Activations Density 0.032%

    No Known Activations