© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20631
    Prev
    Next
    INDEX
    Explanations

    myth and mythology

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

    The main thing this neuron does is detect mentions of “myth” (and its variants) or references to mythology.

    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
     =
    -2.63
    ۔
    -2.59
    灕
    -2.56
    怎么说
    -2.48
    　　「
    -2.38
    ."
    -2.34
     â
    -2.31
    昞
    -2.27
    mallera
    -2.25
    -"
    -2.23
    POSITIVE LOGITS
    .
    3.45
    '
    3.20
    </b>
    2.98
    
    2.47
    K
    2.39
    然后
    2.36
    C
    2.30
    ti
    2.25
     nokt
    2.19
    ورا
    2.13
    Activations Density 0.004%

    No Known Activations