© 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. 34611
    Prev
    Next
    INDEX
    Explanations

    real data

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

    The neuron activates on numeric tokens (sequences of digits) in 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_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
    踉
    -0.90
    ef
    -0.88
    hoon
    -0.85
    हन
    -0.83
    ⬤
    -0.82
    iere
    -0.81
    bis
    -0.81
    both
    -0.81
    ILIO
    -0.81
    parts
    -0.81
    POSITIVE LOGITS
     actual
    1.06
    正常的
    1.02
    正常
    0.95
     conventional
    0.94
     only
    0.93
     บาง
    0.92
    正式
    0.92
     genuine
    0.91
     немає
    0.88
    真正的
    0.88
    Activations Density 0.100%

    No Known Activations