© 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. 15050
    Prev
    Next
    INDEX
    Explanations

    file paths and questions

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

    The neuron activates on numeric literals (numbers) in code or data formats.

    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
     pengar
    -1.13
     herbe
    -1.13
     visuelle
    -1.09
     granat
    -1.08
     gelo
    -1.08
     simpel
    -1.04
     manuelle
    -1.02
     fosfor
    -1.02
     industrielle
    -1.01
     tempel
    -1.01
    POSITIVE LOGITS
     disposiciones
    1.16
     womit
    1.09
    了一些
    1.09
     *,
    1.02
     aquel
    1.01
     gdyż
    1.01
    了不少
    1.00
    Fart
    0.99
     selben
    0.98
    atouille
    0.96
    Activations Density 0.038%

    No Known Activations