© 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. 110765
    Prev
    Next
    INDEX
    Explanations

    mat ending filenames/words

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

    the substring "mat" within technical or code-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    姈
    -2.53
    🦤
    -2.52
    牁
    -2.47
    狁
    -2.45
    ഒ
    -2.44
    hojas
    -2.39
     твоя
    -2.38
    驁
    -2.36
    之道
    -2.34
    energie
    -2.33
    POSITIVE LOGITS
    '
    3.73
    s
    2.95
    O
    2.92
    Z
    2.89
    \
    2.83
    k
    2.77
    M
    2.58
    ar
    2.58
    "
    2.55
    D
    2.52
    Activations Density 0.004%

    No Known Activations