© 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. 103007
    Prev
    Next
    INDEX
    Explanations

    Technical and foreign words

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

    The neuron is specialized to pick out forward‐slash characters (“/”) in the text.

    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
     jeito
    -0.78
     first
    -0.77
    maj
    -0.77
     talento
    -0.73
     dise
    -0.73
     πρώ
    -0.71
    First
    -0.69
     سعود
    -0.69
     FIRST
    -0.69
    first
    -0.69
    POSITIVE LOGITS
    bahar
    0.79
     transmite
    0.69
     視
    0.67
    Factura
    0.65
    летия
    0.64
     xuyên
    0.64
    micha
    0.64
    Firewall
    0.63
    ロウ
    0.63
    alnız
    0.63
    Activations Density 0.046%

    No Known Activations