© 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. 34-GEMMASCOPE-RES-131K
    7. 64737
    Prev
    Next
    INDEX
    Explanations

    file header blocks packet

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

    This neuron fires on numeric tokens and digit‐heavy identifiers, i.e. any standalone numbers or strings containing primarily digits.

    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
    rdom
    -0.79
     inspiração
    -0.77
     städ
    -0.75
     السل
    -0.75
    rimid
    -0.74
     steep
    -0.74
     parallel
    -0.74
    collective
    -0.73
    umsy
    -0.73
     pricey
    -0.73
    POSITIVE LOGITS
     record
    1.33
    record
    1.27
     section
    1.14
     sections
    1.14
    Section
    1.11
     structure
    1.10
    Record
    1.09
     header
    1.08
     records
    1.07
     Record
    1.05
    Activations Density 0.061%

    No Known Activations