© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99698
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron fires on numeric tokens—sequences of digits such as line numbers, IDs, counts, or other numeric literals.

    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
     butik
    -0.75
    ✙
    -0.75
     tider
    -0.74
     ekip
    -0.72
     illustrationer
    -0.72
     intitu
    -0.68
    Ether
    -0.67
     tret
    -0.67
     என
    -0.66
    AMM
    -0.65
    POSITIVE LOGITS
    政
    0.68
    挖掘
    0.68
     Sequ
    0.68
    short
    0.67
     niñas
    0.65
    pipeline
    0.65
    ohio
    0.65
    늙
    0.65
    짧
    0.65
    rschein
    0.64
    Activations Density 0.070%

    No Known Activations