© 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. 38990
    Prev
    Next
    INDEX
    Explanations

    he's / she's

    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
    ophageal
    -2.95
     sportivo
    -2.88
    焄
    -2.72
    𓆜
    -2.72
    เตอร์
    -2.72
    呓
    -2.72
    鴣
    -2.69
     Ottobre
    -2.67
    𔘓
    -2.67
    ينو
    -2.64
    POSITIVE LOGITS
     
    3.56
     been
    3.55
    "
    3.52
     a
    2.88
    -
    2.83
     REALLY
    2.80
    '
    2.77
     i
    2.58
     realmente
    2.56
    really
    2.55
    Activations Density 0.488%

    No Known Activations