© 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. 7163
    Prev
    Next
    INDEX
    Explanations

    words ending in ley

    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
    mapStateToProps
    -2.39
    Z
    -2.38
    AutoresizingMask
    -2.36
    writerow
    -2.28
     которы
    -2.23
    tikzpicture
    -2.22
    تیجه
    -2.22
    镲
    -2.16
    肏
    -2.16
    O
    -2.16
    POSITIVE LOGITS
     Anſ
    2.75
    女性の
    2.73
    ley
    2.59
    )
    2.53
    事を
    2.53
    小孩子
    2.48
    
    2.45
    釭
    2.42
    ри
    2.42
     réfugiés
    2.38
    Activations Density 0.012%

    No Known Activations