© 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. 68148
    Prev
    Next
    INDEX
    Explanations

    URL codes and numbers

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

    The neuron strongly fires on tokens that are short alphanumeric codes—especially those containing digits (e.g. numeric IDs, counters, or parts of 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_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
     in
    -1.68
     should
    -1.44
     on
    -1.42
     with
    -1.38
     throughout
    -1.30
     through
    -1.29
     after
    -1.27
    ジアム
    -1.27
     bär
    -1.25
     by
    -1.24
    POSITIVE LOGITS
    new
    1.47
    six
    1.34
    two
    1.27
    make
    1.27
    four
    1.25
    seven
    1.20
    completely
    1.19
    NEW
    1.17
    ∼
    1.16
    the
    1.14
    Activations Density 0.001%

    No Known Activations