© 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. 225
    Prev
    Next
    INDEX
    Explanations

    Karl and Franz names

    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
    ቷ
    -2.56
     they
    -2.53
     and
    -2.45
     The
    -2.39
    ﺋ
    -2.36
     Familienname
    -2.22
    ’
    -2.22
    ↵↵
    -2.19
     besonders
    -2.17
     ‘
    -2.13
    POSITIVE LOGITS
    .
    3.91
    2
    3.27
    ية
    3.02
    5
    2.67
    N
    2.67
    empêcher
    2.58
    L
    2.53
    วัติ
    2.53
     صغير
    2.52
     autres
    2.50
    Activations Density 0.003%

    No Known Activations