© 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. 75415
    Prev
    Next
    INDEX
    Explanations

    code and configuration files

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

    The neuron strongly activates on standalone numeric literals (integers or decimals) in the 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
     was
    -1.59
    They
    -1.52
     reaffirmed
    -1.46
     is
    -1.41
     they
    -1.38
    alarme
    -1.38
     participaron
    -1.38
     there
    -1.37
    apprentissage
    -1.37
     recientemente
    -1.30
    POSITIVE LOGITS
    therners
    1.59
    iferous
    1.57
    justed
    1.52
    ifier
    1.52
     gustar
    1.51
    }
    1.49
    datable
    1.45
    ̊
    1.45
    hores
    1.43
    mos
    1.40
    Activations Density 0.015%

    No Known Activations