© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6033
    Prev
    Next
    INDEX
    Explanations

    words ending in ance or ence

    np_acts-logits-general · gemini-2.5-flash-lite

    'ance' and 'ence' endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     শিকার
    0.50
    蕌
    0.49
    䀦
    0.49
    㽛
    0.49
    㚼
    0.47
    EventListeners
    0.46
    ➼
    0.46
    ujjati
    0.45
    淍
    0.45
    អ៊ី
    0.45
    POSITIVE LOGITS
    ance
    2.72
    ence
    2.67
    ENCE
    2.34
     ence
    2.31
    ANCE
    2.28
    ances
    2.23
    rence
    2.20
    ences
    2.17
     ance
    2.14
    nce
    2.03
    Activations Density 0.139%

    No Known Activations