© 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. 67944
    Prev
    Next
    INDEX
    Explanations

    background color

    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
    女孩子
    -2.66
     も
    -2.44
     When
    -2.31
     There
    -2.31
    良い
    -2.30
     стал
    -2.28
    甃
    -2.20
    x
    -2.17
    わから
    -2.14
     laden
    -2.11
    POSITIVE LOGITS
    屜
    2.63
    .
    2.63
    <bos>
    2.61
    媗
    2.50
    鯧
    2.47
    ↵
    2.47
    
    2.41
     wn
    2.33
    地说道
    2.31
    蚴
    2.31
    Activations Density 0.016%

    No Known Activations