© 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. 84656
    Prev
    Next
    INDEX
    Explanations

    No such file or directory

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

    This neuron predominantly activates on numeric tokens (i.e. sequences of digits, like error codes or standalone numbers).

    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
    Cham
    -0.78
     Seitz
    -0.77
    новниш
    -0.73
    anyak
    -0.73
     dau
    -0.73
    ffiche
    -0.72
     اسم
    -0.68
    agoza
    -0.67
     SHA
    -0.67
    cles
    -0.67
    POSITIVE LOGITS
    TV
    1.11
     TV
    1.06
     timeval
    1.00
     tv
    0.88
     television
    0.87
    Television
    0.83
    Fernseh
    0.81
     Television
    0.81
    times
    0.80
     times
    0.78
    Activations Density 0.104%

    No Known Activations