© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41171
    Prev
    Next
    INDEX
    Explanations

    indeed followed by affirmation

    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
     {
    -2.98
    鸰
    -2.70
    
    -2.63
     katkı
    -2.55
     strenuous
    -2.47
     deği
    -2.44
     mais
    -2.44
    ೣ
    -2.41
     segura
    -2.39
     önem
    -2.38
    POSITIVE LOGITS
    There
    3.39
    They
    3.30
    (
    2.70
     dante
    2.66
     daniel
    2.59
    It
    2.59
     kazak
    2.58
    That
    2.56
    鄖
    2.52
     joel
    2.47
    Activations Density 0.003%

    No Known Activations