© 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. 33605
    Prev
    Next
    INDEX
    Explanations

    just or only

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

    The neuron is primarily responding to explicit numeric references and quantities (i.e. tokens that denote numbers or numerical “counts” in the 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
     både
    -1.28
     résister
    -1.21
     pourront
    -1.13
    龊
    -1.12
     occuper
    -1.11
     gela
    -1.11
    だけでなく
    -1.10
    奁
    -1.10
     många
    -1.09
     delà
    -1.09
    POSITIVE LOGITS
     only
    1.73
     только
    1.65
     or
    1.47
     тільки
    1.46
     solely
    1.39
     tylko
    1.37
     just
    1.30
     merely
    1.28
     because
    1.25
     alleen
    1.23
    Activations Density 0.037%

    No Known Activations