© 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. 22-GEMMASCOPE-RES-131K
    7. 69036
    Prev
    Next
    INDEX
    Explanations

    file paths and URLs

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

    The neuron fires on tokens that are mainly numeric or digit‐rich sequences (e.g. version numbers, numeric IDs, line numbers).

    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
    camiseta
    -1.21
     disampaikan
    -1.13
    więcej
    -1.11
    ָר
    -1.10
    gunas
    -1.07
     abrigo
    -1.05
    camisa
    -1.05
     what
    -1.04
     amado
    -1.04
     kän
    -1.03
    POSITIVE LOGITS
     cuyos
    1.20
     cuyas
    1.18
     to
    1.14
     VERY
    1.10
     lorsqu
    1.09
     le
    1.09
    u
    1.08
     ~
    1.05
     *
    1.04
     |
    1.04
    Activations Density 0.016%

    No Known Activations