© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93386
    Prev
    Next
    INDEX
    Explanations

    Aviation, volcano, & military ranks

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

    This neuron primarily activates on numeric tokens—especially multi‐digit numbers such as dates, years, phone numbers, and other numerical codes.

    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
    迷
    -0.77
     esperanza
    -0.75
    ValidationError
    -0.73
    Ύ
    -0.73
    macOS
    -0.72
    LDAP
    -0.71
     迷
    -0.69
     Dutton
    -0.69
    最小
    -0.67
    Tracce
    -0.67
    POSITIVE LOGITS
     underwear
    0.92
     Underwear
    0.88
     printer
    0.87
     volcanic
    0.87
     Volcanic
    0.86
     Schreib
    0.85
    ilibre
    0.83
    ൾ
    0.79
     printing
    0.78
    Plots
    0.77
    Activations Density 0.026%

    No Known Activations