© 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. 60116
    Prev
    Next
    INDEX
    Explanations

    Get affordable prints

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

    The neuron is primarily triggered by numeric tokens (digits and numbers) appearing in the document, especially in code or parameter settings.

    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
    プリング
    -0.82
    リティ
    -0.75
    prototype
    -0.75
    james
    -0.74
    falt
    -0.71
    names
    -0.71
    厂家
    -0.70
     about
    -0.70
     निर्देश
    -0.69
     entertained
    -0.69
    POSITIVE LOGITS
     counters
    1.09
    errHandler
    0.94
    Counters
    0.89
    Roman
    0.88
    limard
    0.85
     roman
    0.84
     counter
    0.84
     câu
    0.80
     Arabic
    0.79
    brom
    0.79
    Activations Density 0.009%

    No Known Activations