© 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. 21876
    Prev
    Next
    INDEX
    Explanations

    but

    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
     andare
    -1.85
    檩
    -1.77
    Öl
    -1.74
     problèmes
    -1.70
    叆
    -1.69
    下意识
    -1.67
     ensalada
    -1.58
     BECAUSE
    -1.54
     ferie
    -1.54
    vänt
    -1.52
    POSITIVE LOGITS
     to
    3.13
     but
    2.44
     before
    2.34
     as
    2.23
     without
    2.19
     if
    1.89
     in
    1.81
     having
    1.80
     both
    1.80
     make
    1.76
    Activations Density 0.078%

    No Known Activations