© 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. 22-GEMMASCOPE-RES-131K
    7. 38786
    Prev
    Next
    INDEX
    Explanations

    . followed by conditional or consequential words

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

    The neuron strongly activates on numeric literals and numeric configuration values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    yoruz
    -1.04
    тература
    -1.02
    ด้วย
    -0.96
    其次
    -0.95
    竟然
    -0.94
    ethene
    -0.92
    ாம்
    -0.92
    alisme
    -0.91
    ють
    -0.91
     alebo
    -0.91
    POSITIVE LOGITS
     therefore
    1.90
     if
    1.64
     so
    1.50
     thus
    1.48
     you
    1.48
    Therefore
    1.36
    If
    1.27
     поэтому
    1.27
     Therefore
    1.19
     thereby
    1.18
    Activations Density 0.108%

    No Known Activations