© 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. 72905
    Prev
    Next
    INDEX
    Explanations

    punctuation preceding month/year or specific technical terms

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

    The neuron strongly activates on numeric tokens (e.g. version numbers, integers, percentages) in code or text.

    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
     pérd
    -1.97
     TÉ
    -1.88
     romantis
    -1.87
     italiens
    -1.84
     textil
    -1.82
     kalender
    -1.80
     nacht
    -1.73
     ché
    -1.73
     Septembre
    -1.73
     protokol
    -1.73
    POSITIVE LOGITS
     and
    1.70
     This
    1.60
     With
    1.48
     will
    1.47
     These
    1.42
     beschäftigen
    1.41
    ようです
    1.39
     asemenea
    1.37
    ↵↵
    1.36
     womit
    1.34
    Activations Density 0.003%

    No Known Activations