© 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. 34-GEMMASCOPE-RES-131K
    7. 48276
    Prev
    Next
    INDEX
    Explanations

    publishing house, publishers, companies

    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_34/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
    欽
    -0.76
    Вз
    -0.68
     delegate
    -0.68
     šte
    -0.67
     Hv
    -0.66
     Tertiary
    -0.66
    上品
    -0.66
     تحلیل
    -0.66
     chi̍t
    -0.66
    rifty
    -0.66
    POSITIVE LOGITS
    ņu
    0.85
     Geistes
    0.80
     Publishing
    0.80
    ()(
    0.80
    աք
    0.78
     warrior
    0.76
    ₽
    0.75
     annoncé
    0.74
    ствую
    0.73
    wheeler
    0.73
    Activations Density 0.009%

    No Known Activations