© 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. 99731
    Prev
    Next
    INDEX
    Explanations

    cin as prefix

    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
     of
    -2.81
     a
    -2.78
     innych
    -2.66
    鈇
    -2.55
     Bestandteil
    -2.50
    the
    -2.45
    
    -2.34
    ⸨
    -2.33
    袮
    -2.31
    雰
    -2.28
    POSITIVE LOGITS
    
    3.14
    翃
    2.92
    齮
    2.80
    transQ
    2.69
     Diſ
    2.66
    鉭
    2.56
    ⎚
    2.52
    ⃙
    2.48
     saine
    2.47
    𐑂
    2.45
    Activations Density 0.008%

    No Known Activations