© 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. 42802
    Prev
    Next
    INDEX
    Explanations

    market share or penetration

    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
     it
    -1.80
    vestido
    -1.69
    女
    -1.67
    🩻
    -1.61
    іга
    -1.59
    餿
    -1.58
    ğına
    -1.55
    vierten
    -1.55
    Ћ
    -1.54
    teza
    -1.51
    POSITIVE LOGITS
    le
    1.95
    c
    1.88
    e
    1.76
    heute
    1.70
    ㌧
    1.70
    h
    1.69
    m
    1.69
    i
    1.66
    for
    1.64
    その他の
    1.63
    Activations Density 0.014%

    No Known Activations