© 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. 47449
    Prev
    Next
    INDEX
    Explanations

    United States, noninstitutional, interviewed

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

    The neuron fires strongly on numeric tokens—digits, multi‐digit numbers, and related numeric notation.

    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
     macroeconomic
    -0.76
    norsk
    -0.75
     मौ
    -0.74
    rüstung
    -0.73
    なんですね
    -0.71
     Estadística
    -0.71
    Unemployment
    -0.69
     onCreateView
    -0.69
    եղ
    -0.68
    وافق
    -0.68
    POSITIVE LOGITS
    lief
    0.81
     articol
    0.81
    ttps
    0.75
     GOES
    0.75
    cheque
    0.75
    getPage
    0.75
     Lade
    0.74
     jajaran
    0.72
    DateFormat
    0.72
    edu
    0.71
    Activations Density 0.073%

    No Known Activations