© 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. 129860
    Prev
    Next
    INDEX
    Explanations

    is/are/do/does/did/can/will + noun/pronoun

    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
    .”
    -1.81
    If
    -1.77
    </blockquote>
    -1.73
    7
    -1.70
    <b>
    -1.58
     If
    -1.56
    Those
    -1.56
    \
    -1.53
    有一天
    -1.50
    如果有
    -1.47
    POSITIVE LOGITS
     about
    1.85
     a
    1.49
     eiland
    1.38
    imetsu
    1.37
    
    1.36
    entarios
    1.35
     XXXIV
    1.34
     Waar
    1.34
    🏝
    1.30
    鐿
    1.30
    Activations Density 0.005%

    No Known Activations