© 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. 23884
    Prev
    Next
    INDEX
    Explanations

    hexadecimal, hex colors, and hexoses

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

    The neuron fires on any occurrence of “hex” (as part of identifiers, strings, or comments) indicating references to hexadecimal data.

    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
    縂
    -2.69
    
    -2.50
    袮
    -2.41
    }
    -2.41
    擼
    -2.39
    á
    -2.39
    </h5>
    -2.39
    綃
    -2.38
    螓
    -2.31
    糌
    -2.31
    POSITIVE LOGITS
     '
    2.66
    沺
    2.33
    \
    2.31
    IFYING
    2.25
    ugeot
    2.20
     知道
    2.17
    しっかり
    2.14
    :
    2.06
    硖
    2.03
    asnya
    2.02
    Activations Density 0.004%

    No Known Activations