© 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. 22-GEMMASCOPE-RES-131K
    4. 80008
    Prev
    Next
    INDEX
    Explanations

    connecting listed names

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

    The neuron strongly activates on three-digit numeric tokens.

    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
     or
    -1.11
     sábado
    -1.01
    寝る
    -0.99
     çalışmalar
    -0.99
     primeira
    -0.98
     and
    -0.98
     целью
    -0.98
     algunas
    -0.98
    合う
    -0.96
    nyataan
    -0.96
    POSITIVE LOGITS
     immensely
    1.06
    Здравствуйте
    1.06
     predeceased
    1.02
     evitare
    1.02
     épouse
    0.98
     ironically
    0.98
     interestingly
    0.98
     pittura
    0.97
    никах
    0.96
     wünscht
    0.96
    Activations Density 0.001%

    No Known Activations