© 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. 64799
    Prev
    Next
    INDEX
    Explanations

    c/c++ declarations and struct definitions

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

    The neuron fires on standalone numeric tokens (i.e. sequences of digits representing 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
     forks
    -0.86
     Forks
    -0.78
     octo
    -0.78
    Prairie
    -0.75
    setSelected
    -0.74
    ulaire
    -0.72
    ungguhnya
    -0.72
    шу
    -0.70
    ENCES
    -0.69
     Thirteenth
    -0.68
    POSITIVE LOGITS
    register
    1.39
     register
    1.11
     int
    0.96
    olyte
    0.87
     registering
    0.86
    int
    0.86
    extern
    0.85
     short
    0.85
    short
    0.83
     registration
    0.83
    Activations Density 0.026%

    No Known Activations