© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85596
    Prev
    Next
    INDEX
    Explanations

    MDA, image text, buttons

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

    The neuron selectively fires on floating‐point numeric tokens—i.e. decimal measurements in the 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_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
    </b>
    -2.69
    ization
    -2.66
    3
    -2.59
    特别的
    -2.52
    齪
    -2.39
    明显的
    -2.33
    ┿
    -2.22
    ity
    -2.20
    很是
    -2.14
    }
    -2.11
    POSITIVE LOGITS
    鲠
    3.39
    琹
    3.06
    蕷
    2.92
    塒
    2.70
     puede
    2.67
    ሖ
    2.58
    ৣ
    2.55
    杁
    2.53
    condido
    2.52
    摶
    2.48
    Activations Density 0.005%

    No Known Activations