© 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. 57373
    Prev
    Next
    INDEX
    Explanations

    char array programming

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

    This neuron does not reliably activate on any particular tokens or patterns—it effectively finds nothing.

    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
    勦
    -2.97
    
    -2.78
    狴
    -2.78
    鳢
    -2.77
    ing
    -2.50
    geſ
    -2.47
    laught
    -2.42
    錵
    -2.42
    н
    -2.38
    
    -2.38
    POSITIVE LOGITS
    1
    4.56
    2
    3.81
    3
    3.80
    6
    3.59
    5
    3.50
    9
    3.22
    7
    3.08
    8
    2.83
    0
    2.81
    For
    2.69
    Activations Density 0.001%

    No Known Activations