© 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. 34-GEMMASCOPE-RES-131K
    7. 32487
    Prev
    Next
    INDEX
    Explanations

    API endpoints

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

    The neuron fires on numeric tokens (digits or numbers) such as port numbers, version numbers, or other numeric literals in code and URLs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Elementos
    -0.81
    昶
    -0.80
     vencer
    -0.76
    /{
    -0.75
    ZZZZ
    -0.75
    шкина
    -0.75
    atleta
    -0.75
     remercie
    -0.73
     after
    -0.73
    lampada
    -0.72
    POSITIVE LOGITS
    api
    3.59
     api
    2.83
     API
    2.17
    API
    2.03
     Api
    1.72
    Api
    1.68
     APIs
    1.40
    graphql
    1.23
    Apis
    1.14
    WebAPI
    1.09
    Activations Density 0.018%

    No Known Activations