© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31738
    Prev
    Next
    INDEX
    Explanations

    heated tools or processes

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

    The neuron specifically detects numeric tokens (i.e. numbers and digit sequences) 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_34/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
    робі
    -0.79
     soft
    -0.75
     Thiel
    -0.73
    oteur
    -0.71
    ossed
    -0.71
    iliar
    -0.71
    ޯ
    -0.70
    AGM
    -0.69
    ünd
    -0.69
    etra
    -0.69
    POSITIVE LOGITS
     irons
    2.88
     iron
    2.47
     Irons
    2.17
     Iron
    2.05
    Iron
    2.00
     ironing
    1.86
    iron
    1.80
    IRON
    1.75
     IRON
    1.66
     curling
    1.44
    Activations Density 0.022%

    No Known Activations