© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75229
    Prev
    Next
    INDEX
    Explanations

    creation, light, reign

    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
     some
    -1.92
    .......
    -1.77
    …..
    -1.76
     just
    -1.75
     (
    -1.75
     When
    -1.73
     на
    -1.72
    ........
    -1.69
    .....
    -1.69
    !!
    -1.66
    POSITIVE LOGITS
     aislados
    1.94
     animados
    1.94
     instruk
    1.91
     certamente
    1.90
    ambut
    1.83
    靦
    1.82
     evidentemente
    1.81
    jourd
    1.81
    lokal
    1.78
    kanak
    1.76
    Activations Density 0.019%

    No Known Activations