© 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. 38746
    Prev
    Next
    INDEX
    Explanations

    prices and subscriptions

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

    The neuron activates on numerical price or fee mentions (currency amounts).

    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
     materials
    -1.38
     his
    -1.38
     these
    -1.34
     similar
    -1.32
     important
    -1.30
     letto
    -1.30
     those
    -1.28
     food
    -1.27
     some
    -1.24
     kembali
    -1.24
    POSITIVE LOGITS
     you
    1.73
     Eſ
    1.49
    鳚
    1.43
     your
    1.42
    ffichage
    1.39
     comportements
    1.34
    咂
    1.33
     viennent
    1.30
     gelişti
    1.30
     Inicial
    1.27
    Activations Density 0.018%

    No Known Activations