© 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. 22-GEMMASCOPE-RES-131K
    7. 71402
    Prev
    Next
    INDEX
    Explanations

    requests for information

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

    The neuron activates on hexadecimal numerals (digits and letters) in code—i.e. parts of hex constants or addresses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Accesorios
    -0.99
     thánh
    -0.96
     imprimée
    -0.94
    urige
    -0.94
    VEHICLE
    -0.94
    ändern
    -0.90
     советы
    -0.90
     Samsung
    -0.89
     Unters
    -0.88
     imprimé
    -0.88
    POSITIVE LOGITS
     уточ
    0.95
    晄
    0.94
     Это
    0.92
     ざ
    0.92
     solteiro
    0.90
     veröffentlich
    0.85
     این
    0.85
    cially
    0.82
     rotas
    0.82
     Poster
    0.82
    Activations Density 0.000%

    No Known Activations