© 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. 72344
    Prev
    Next
    INDEX
    Explanations

    locations and countries

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

    The neuron detects numeric tokens—especially multi‐digit numbers representing counts, statistics, or measurement data.

    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
     that
    -1.73
     because
    -1.56
     then
    -1.54
     not
    -1.53
     possibly
    -1.52
     suggested
    -1.52
     using
    -1.46
     any
    -1.43
     potentially
    -1.42
     people
    -1.41
    POSITIVE LOGITS
     siè
    1.39
     assurent
    1.38
     ストラップ
    1.35
     ジップ
    1.35
     honn
    1.34
     flotte
    1.30
     marche
    1.30
     faciliter
    1.30
     rése
    1.28
     formid
    1.26
    Activations Density 0.047%

    No Known Activations