© 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. 105115
    Prev
    Next
    INDEX
    Explanations

    wind turbines and sailboats

    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
     of
    -1.41
    .
    -1.30
    íd
    -1.24
    )];
    -1.23
     degener
    -1.20
    série
    -1.19
     Reſ
    -1.19
    ={`
    -1.15
     frattempo
    -1.15
     '.',
    -1.14
    POSITIVE LOGITS
    风
    1.54
     wind
    1.44
     encontrado
    1.37
    欧式
    1.25
    Statistiche
    1.20
     breezes
    1.19
     begann
    1.18
     systemu
    1.18
    風
    1.17
    UCIÓN
    1.16
    Activations Density 0.062%

    No Known Activations