© 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. 67598
    Prev
    Next
    INDEX
    Explanations

    technical/scientific abbreviations

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

    The neuron specifically detects the standalone digit “8.”

    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
     ?
    -1.02
     type
    -1.00
     nóng
    -0.97
     empezar
    -0.96
    に来て
    -0.92
     who
    -0.91
    chaise
    -0.91
     like
    -0.90
     metálica
    -0.90
     such
    -0.90
    POSITIVE LOGITS
    Ꮠ
    1.14
     motivi
    1.09
    ⃢
    1.02
     patrie
    1.00
    ‚¬
    1.00
    晚上
    0.99
    ῞
    0.99
    mbolic
    0.99
    sions
    0.98
     печи
    0.97
    Activations Density 0.000%

    No Known Activations