© 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. 47794
    Prev
    Next
    INDEX
    Explanations

    launching investigations and actions

    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
     some
    -1.65
    贗
    -1.49
     that
    -1.49
     places
    -1.43
    了一个
    -1.38
    了一個
    -1.38
     one
    -1.37
    omalies
    -1.35
     Küsten
    -1.34
     gillar
    -1.32
    POSITIVE LOGITS
    就可以
    1.73
    .”
    1.70
     to
    1.69
     remarquer
    1.50
     cercando
    1.41
     disponibile
    1.40
    徊
    1.40
     numéros
    1.39
     campagnes
    1.39
    ;
    1.39
    Activations Density 0.077%

    No Known Activations