© 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. 34-GEMMASCOPE-RES-131K
    7. 34776
    Prev
    Next
    INDEX
    Explanations

    billing codes

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

    The neuron strongly activates on article or question titles and headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ācijas
    -0.88
    cuk
    -0.79
     autem
    -0.78
    itres
    -0.78
     mezza
    -0.77
    kona
    -0.77
     venire
    -0.75
    ofil
    -0.74
     Dud
    -0.73
    ള്ള
    -0.72
    POSITIVE LOGITS
     codes
    1.73
     Codes
    1.41
     CPT
    1.34
     coding
    1.30
     códigos
    1.30
    codes
    1.29
     code
    1.26
    Codes
    1.25
     коды
    1.23
    CODES
    1.18
    Activations Density 0.023%

    No Known Activations