© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50190
    Prev
    Next
    INDEX
    Explanations

    package and import paths

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

    The neuron detects tokens that consist primarily of numeric sequences (digits), such as version numbers or numeric identifiers in code.

    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
    iade
    -1.27
    Andere
    -1.20
    さっき
    -1.16
     mūsų
    -1.14
    你来
    -1.13
     Lijst
    -1.07
     Если
    -1.06
     jūsų
    -1.05
    你自己
    -1.05
     oposición
    -1.05
    POSITIVE LOGITS
     util
    1.21
    specific
    1.13
    饌
    1.13
     posible
    1.10
     until
    1.10
     ciel
    1.09
     acom
    1.09
    util
    1.08
     acept
    1.07
     naveg
    1.05
    Activations Density 0.065%

    No Known Activations