© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8724
    Prev
    Next
    INDEX
    Explanations

    questions beginning with how

    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
    alakip
    -1.80
    copie
    -1.79
     rivi
    -1.77
    媵
    -1.77
     vider
    -1.77
    闼
    -1.77
    
    -1.77
     automne
    -1.76
     benzin
    -1.75
    captain
    -1.73
    POSITIVE LOGITS
    After
    2.19
    When
    2.03
     if
    1.98
    after
    1.97
    During
    1.95
    S
    1.93
    when
    1.88
    R
    1.88
    While
    1.85
    Even
    1.85
    Activations Density 0.041%

    No Known Activations