© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75777
    Prev
    Next
    INDEX
    Explanations

    don't get me wrong

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

    The neuron activates on numeric tokens—particularly multi‐digit numbers (e.g. years or large counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -3.89
     of
    -2.55
     in
    -2.20
     to
    -2.02
     or
    -1.98
     for
    -1.92
     from
    -1.77
     (
    -1.71
     on
    -1.71
     like
    -1.70
    POSITIVE LOGITS
    ,
    2.88
    ،
    1.77
     vendeur
    1.50
     imprimer
    1.45
     jopa
    1.45
     avocat
    1.43
     empêcher
    1.43
     recev
    1.43
     romantis
    1.41
     Comprar
    1.41
    Activations Density 0.093%

    No Known Activations