© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11868
    Prev
    Next
    INDEX
    Explanations

    annual meetings and conventions

    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
     are
    -1.86
     όταν
    -1.67
    痦
    -1.66
     employ
    -1.63
    5
    -1.63
     omdat
    -1.62
     exemplify
    -1.60
    ?
    -1.59
     které
    -1.57
     preuß
    -1.53
    POSITIVE LOGITS
    鹟
    2.05
    鲥
    2.02
     camiset
    1.95
    
    1.91
     parachoque
    1.77
     of
    1.74
    ܜ
    1.65
    𓍊
    1.63
    🫓
    1.59
     vieux
    1.59
    Activations Density 0.008%

    No Known Activations