© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39197
    Prev
    Next
    INDEX
    Explanations

    speeches and parliamentary proceedings

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

    The neuron primarily responds to numeric tokens (dates, years, measurements, and other multi-digit numbers).

    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
     it
    -1.55
    ֢
    -1.36
     wasn
    -1.34
     isn
    -1.32
     encontré
    -1.30
     verdadera
    -1.28
    🦳
    -1.26
     anahtar
    -1.23
     hermos
    -1.22
     basado
    -1.22
    POSITIVE LOGITS
    🪛
    1.84
    暧
    1.69
    نے
    1.38
     professores
    1.34
    dirond
    1.34
    thè
    1.33
    🧫
    1.32
    tioned
    1.29
    capulco
    1.28
     decy
    1.27
    Activations Density 0.022%

    No Known Activations