© 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. 1126
    Prev
    Next
    INDEX
    Explanations

    update function

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

    The neuron is picking up on numeric literals (i.e. standalone numbers) in the code or 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
     dueños
    -0.82
    *~
    -0.79
    *]
    -0.77
     След
    -0.77
     Frucht
    -0.77
     instalação
    -0.76
     dör
    -0.75
    Atentamente
    -0.75
     beginnings
    -0.72
    Pras
    -0.72
    POSITIVE LOGITS
     Update
    2.03
     update
    1.84
    update
    1.71
    Update
    1.65
     UPDATE
    1.63
    UPDATE
    1.63
     updates
    1.40
    onUpdate
    1.30
    更新
    1.26
     Updates
    1.22
    Activations Density 0.002%

    No Known Activations