© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66952
    Prev
    Next
    INDEX
    Explanations

    existence checks

    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
    1
    -2.78
    a
    -2.52
    ఽ
    -2.44
    拊
    -2.39
    el
    -2.39
     ་
    -2.34
    聽到
    -2.30
    ised
    -2.28
    鶺
    -2.22
    
    -2.20
    POSITIVE LOGITS
    寕
    2.55
    ᳝
    2.36
    鏨
    2.34
    TryDecode
    2.22
    \
    2.03
    ጵ
    2.03
    ptonshire
    2.00
     There
    2.00
    м
    1.99
    ()){
    1.98
    Activations Density 0.003%

    No Known Activations