© 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. 130225
    Prev
    Next
    INDEX
    Explanations

    deadline dates and events

    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
    Démographie
    -1.64
    apparently
    -1.61
    Unfortunately
    -1.54
    냑
    -1.53
    byshev
    -1.50
    supposed
    -1.47
     різних
    -1.44
    significantly
    -1.43
     ordres
    -1.42
     necessari
    -1.42
    POSITIVE LOGITS
    F
    1.84
    '
    1.69
     económicas
    1.66
    ="
    1.66
    ing
    1.63
     time
    1.59
    _{
    1.58
    I
    1.44
    un
    1.43
    ud
    1.43
    Activations Density 0.008%

    No Known Activations