© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93109
    Prev
    Next
    INDEX
    Explanations

    District Court of Appeal

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

    The neuron is detecting large numeric tokens (multi‐digit numbers) such as citation/report volume numbers and numeric attribute values.

    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
    rugs
    -0.74
    ກ
    -0.66
    unpack
    -0.66
     Saving
    -0.63
     rugs
    -0.63
     Set
    -0.63
     Class
    -0.61
    arai
    -0.61
    setof
    -0.60
    noStroke
    -0.60
    POSITIVE LOGITS
     courteous
    0.75
     vettoriale
    0.75
     rejoint
    0.73
    燁
    0.72
     @{
    0.72
    Willem
    0.72
    JsonHelper
    0.72
     unaweza
    0.71
     ביצ
    0.70
    Produkt
    0.68
    Activations Density 0.051%

    No Known Activations