© 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. 10-GEMMASCOPE-RES-131K
    7. 130095
    Prev
    Next
    INDEX
    Explanations

    number or code identifiers followed by values

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

    The neuron fires on numeric references—actual digits or number‐related words (e.g. “numbers,” “编号,” numeric identifiers).

    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
    ]
    -3.23
    敉
    -2.52
    (
    -2.42
    這
    -2.38
    。
    -2.28
    ︲
    -2.27
    ну
    -2.22
    .?
    -2.16
    这种
    -2.16
     trouvé
    -2.13
    POSITIVE LOGITS
    蕷
    2.45
    
    2.42
    ↵
    2.13
    逐渐
    2.09
    耸
    2.06
    顿时
    2.05
    Solución
    2.05
     GEOLOGY
    1.99
    老爷子
    1.98
    いっ
    1.98
    Activations Density 0.002%

    No Known Activations