© 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. 10-GEMMASCOPE-RES-131K
    7. 61182
    Prev
    Next
    INDEX
    Explanations

    names starting with specific sequences

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

    The neuron activates on numeric tokens—especially floating‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鈇
    -2.78
    恿
    -2.66
    亖
    -2.66
    ༷
    -2.53
    芣
    -2.52
    嫫
    -2.41
    洐
    -2.33
    敺
    -2.33
    俢
    -2.30
    对他
    -2.20
    POSITIVE LOGITS
    '
    2.83
    </strong>
    2.72
    </h3>
    2.48
    讴
    2.45
     Then
    2.42
    嚶
    2.33
     powinna
    2.27
    忪
    2.25
     organize
    2.22
    选择
    2.20
    Activations Density 0.001%

    No Known Activations