© 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. 39044
    Prev
    Next
    INDEX
    Explanations

    starting price

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

    The neuron fires on numeric expressions—especially prices, currencies, and other number‐based 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_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
     that
    -1.39
     was
    -0.96
    ternut
    -0.94
     its
    -0.91
     verfolgt
    -0.91
     totality
    -0.89
     pesante
    -0.88
    atecas
    -0.88
     Siamo
    -0.88
    میز
    -0.87
    POSITIVE LOGITS
     start
    1.53
     depending
    1.25
     starts
    1.25
     starting
    1.23
     kezd
    1.16
    start
    1.16
     начать
    1.16
     даже
    1.15
     beginnen
    1.11
    begin
    1.10
    Activations Density 0.008%

    No Known Activations