© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69169
    Prev
    Next
    INDEX
    Explanations

    financial transaction details

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

    This neuron flags numeric tokens—numbers or digits used as ratings, measurements, IDs, or other quantified 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
     will
    -1.09
     can
    -0.99
     hvilke
    -0.98
     kvinder
    -0.96
    izando
    -0.95
     helps
    -0.94
    Смотрите
    -0.94
     grecque
    -0.94
     подарки
    -0.94
    ˅
    -0.93
    POSITIVE LOGITS
     TÉCNICA
    1.18
     esconder
    1.14
    ellery
    1.14
     trhu
    1.05
     Menjadi
    1.04
     cachorros
    1.04
     gâ
    1.03
    ゔ
    1.03
    Hozzá
    1.02
    だわ
    1.02
    Activations Density 0.071%

    No Known Activations