© 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. 91458
    Prev
    Next
    INDEX
    Explanations

    legal citations and code preambles

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

    The neuron activates on numeric tokens (digits or numbers) whenever they appear 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
     specifying
    -0.75
    bbles
    -0.69
     meaning
    -0.69
    termine
    -0.67
    旁
    -0.67
    ceive
    -0.66
    ۂ
    -0.65
     Pais
    -0.64
    illet
    -0.64
    所说的
    -0.64
    POSITIVE LOGITS
     Funktions
    0.73
    McC
    0.68
     sedan
    0.68
    кога
    0.68
     pred
    0.66
     indecent
    0.66
    IAR
    0.66
    usan
    0.65
    SEARCH
    0.65
     центра
    0.64
    Activations Density 0.077%

    No Known Activations