© 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. 10-GEMMASCOPE-RES-131K
    7. 41361
    Prev
    Next
    INDEX
    Explanations

    proper nouns like Lily, Lam, Manhattan

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

    This neuron detects numeric monetary amounts (prices) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    stoffen
    -1.36
    Athe
    -1.34
     않습니다
    -1.24
    ленный
    -1.19
    深夜
    -1.19
    toa
    -1.19
    ̀i
    -1.19
     menatap
    -1.19
    Vå
    -1.17
     bestem
    -1.16
    POSITIVE LOGITS
    their
    1.75
     ihre
    1.57
     time
    1.52
     первого
    1.49
     leur
    1.45
     ihren
    1.45
     '
    1.44
     рядом
    1.41
    âmara
    1.41
     swoją
    1.39
    Activations Density 0.125%

    No Known Activations