© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86909
    Prev
    Next
    INDEX
    Explanations

    words ending in ence

    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
    媜
    -2.61
    栳
    -2.52
    厖
    -2.45
     podía
    -2.42
    The
    -2.42
    蘩
    -2.39
    廕
    -2.39
     encompassing
    -2.39
    轻声
    -2.38
     έχουν
    -2.36
    POSITIVE LOGITS
    崀
    2.58
    ↵↵
    2.53
    เขา
    2.52
     him
    2.36
    ences
    2.31
     of
    2.28
    𝄆
    2.28
    趼
    2.22
    ↵↵↵↵↵↵↵↵↵↵
    2.19
    䊐
    2.19
    Activations Density 0.015%

    No Known Activations