© 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. 41607
    Prev
    Next
    INDEX
    Explanations

    S

    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
     DevComponents
    -1.60
    郸
    -1.55
     Вікіпе
    -1.48
    â
    -1.48
     our
    -1.48
    ("")]
    -1.47
     ('
    -1.46
     because
    -1.44
    (":");
    -1.42
    ptonshire
    -1.41
    POSITIVE LOGITS
    referred
    1.63
     買
    1.59
    ↵
    1.59
    
    1.57
    frequently
    1.57
    believe
    1.55
    thirty
    1.54
    somebody
    1.53
    commonly
    1.50
    despite
    1.48
    Activations Density 0.030%

    No Known Activations