© 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. 13324
    Prev
    Next
    INDEX
    Explanations

    the specific noun

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

    The neuron activates on standalone numeric tokens (numbers or numerical values) 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
    itern
    -1.54
     regiões
    -1.41
     interesses
    -1.38
    definitely
    -1.30
    amanda
    -1.30
    pions
    -1.30
    jow
    -1.28
     roś
    -1.23
     cinq
    -1.23
     lanzó
    -1.23
    POSITIVE LOGITS
     each
    1.50
     it
    1.47
     particular
    1.37
     may
    1.31
    <bos>
    1.30
     with
    1.29
     request
    1.27
    著名
    1.25
     serves
    1.20
     chosen
    1.17
    Activations Density 0.067%

    No Known Activations