© 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. 41406
    Prev
    Next
    INDEX
    Explanations

    ini and properties configuration

    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
     It
    -1.76
    In
    -1.52
     can
    -1.48
        
    -1.47
    0
    -1.41
    This
    -1.39
     is
    -1.34
     to
    -1.33
     even
    -1.33
    to
    -1.31
    POSITIVE LOGITS
    呔
    1.58
    とおり
    1.55
    삵
    1.51
     vaisseaux
    1.50
    鿬
    1.50
     superbes
    1.45
     guapo
    1.44
     employés
    1.44
     icône
    1.43
     véritables
    1.43
    Activations Density 0.021%

    No Known Activations