© 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. 110608
    Prev
    Next
    INDEX
    Explanations

    following numbers or letters

    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
    The
    -2.77
    .
    -2.50
    鹇
    -2.27
     were
    -2.05
    fficio
    -2.02
     essenciais
    -2.00
     tocó
    -2.00
    apatalk
    -1.89
    蠵
    -1.87
    <em>
    -1.80
    POSITIVE LOGITS
    en
    2.22
    鼱
    2.17
    簠
    2.17
    锱
    2.05
    y
    2.03
    躂
    1.95
    樒
    1.90
    d
    1.90
    erintah
    1.88
    rennt
    1.86
    Activations Density 0.016%

    No Known Activations