© 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. 100175
    Prev
    Next
    INDEX
    Explanations

    misc or miscellaneous

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

    The neuron detects occurrences of the identifier “misc” in import/include or dependency lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     It
    -3.22
    氿
    -2.55
    
    -2.53
    </b>
    -2.48
     😀
    -2.45
    ている
    -2.42
    疑惑
    -2.39
    抉
    -2.39
    
    -2.36
    恫
    -2.34
    POSITIVE LOGITS
    6
    3.70
    5
    3.64
    7
    3.50
    3
    3.44
    8
    3.31
    .
    3.30
    4
    3.25
    1
    3.23
    9
    2.77
    𞤢
    2.69
    Activations Density 0.003%

    No Known Activations