© 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. 40749
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 97

    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
    0
    -2.50
    9
    -2.39
     аккура
    -2.20
    7
    -2.20
    8
    -2.19
     подой
    -2.14
     интел
    -2.11
    uttgart
    -2.09
    2
    -2.09
     своє
    -2.08
    POSITIVE LOGITS
     vollständige
    2.69
    ’
    2.59
     offizielle
    2.25
    ↵
    2.23
    AutoresizingMask
    2.11
     genaue
    2.08
     parís
    2.06
     ‘’
    2.05
     bancaria
    2.05
     they
    2.02
    Activations Density 0.014%

    No Known Activations