© 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. 110964
    Prev
    Next
    INDEX
    Explanations

    poorly performed or damaged states

    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
     皇族
    -3.06
    秕
    -3.00
    杙
    -2.77
    趼
    -2.75
    鳙
    -2.72
    ᯾
    -2.70
    
    -2.70
    delicious
    -2.63
    蠵
    -2.61
    Nii
    -2.58
    POSITIVE LOGITS
    one
    3.53
    what
    3.47
    3
    3.44
    s
    3.44
    is
    3.44
    7
    3.41
    re
    3.38
    8
    3.36
    a
    3.33
    2
    3.28
    Activations Density 0.003%

    No Known Activations