© 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. 22-GEMMASCOPE-RES-131K
    7. 25293
    Prev
    Next
    INDEX
    Explanations

    let x be

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

    The neuron fires on numeric tokens (digits and numbers) in mathematical or tabular contexts.

    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
     évidence
    -1.13
    standes
    -1.06
    Kelas
    -0.99
    ль
    -0.98
    視野
    -0.97
    不
    -0.96
    上げます
    -0.95
     reyes
    -0.95
     På
    -0.94
    艤
    -0.94
    POSITIVE LOGITS
    を書く
    1.27
     utilizz
    1.22
    を読んで
    1.20
     riten
    1.16
    を読
    1.16
    完成です
    1.13
    ❧
    1.10
     sapere
    1.09
    に追加
    1.07
    ほら
    1.05
    Activations Density 0.011%

    No Known Activations