© 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. 10-GEMMASCOPE-RES-131K
    7. 13024
    Prev
    Next
    INDEX
    Explanations

    other languages

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

    The neuron consistently activates on numerical quantity tokens (cardinal numbers and numeric measurements, including decimals) indicating counts or 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_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
     what
    -1.83
     because
    -1.50
     arī
    -1.38
     these
    -1.38
     Even
    -1.34
     even
    -1.33
     will
    -1.27
     eigenen
    -1.26
    なんですが
    -1.22
     their
    -1.16
    POSITIVE LOGITS
     других
    1.98
    他の
    1.96
     другие
    1.84
     other
    1.83
     others
    1.64
    其他的
    1.61
    其它
    1.53
     innych
    1.51
    其他
    1.48
     други
    1.46
    Activations Density 0.075%

    No Known Activations