© 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. 128894
    Prev
    Next
    INDEX
    Explanations

    possessive '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
    ).
    -2.25
    It
    -2.03
    4
    -1.70
     p
    -1.66
    el
    -1.65
     and
    -1.64
     (
    -1.64
     system
    -1.63
    This
    -1.62
    5
    -1.60
    POSITIVE LOGITS
    
    1.71
    阏
    1.66
     outubro
    1.64
     内衣
    1.57
    垕
    1.56
    皤
    1.56
    zeichneten
    1.54
    蹀
    1.54
    stande
    1.54
    nowa
    1.54
    Activations Density 0.061%

    No Known Activations