© 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. 63320
    Prev
    Next
    INDEX
    Explanations

    wood burning stove

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

    The neuron is keyed to spotting numeric quantities and related measurement terms (e.g. digits, units, and counts).

    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
    iotensin
    -0.84
    ייט
    -0.81
    оны
    -0.81
    保險
    -0.79
     pintar
    -0.79
     jockey
    -0.78
    ㄅ
    -0.77
     风格
    -0.76
    Writ
    -0.73
     ملك
    -0.72
    POSITIVE LOGITS
     wood
    4.28
     firewood
    3.89
    Wood
    3.16
    wood
    3.13
     Wood
    2.98
    WOOD
    2.80
     WOOD
    2.69
     fuel
    2.33
     woods
    2.27
     leña
    2.20
    Activations Density 0.033%

    No Known Activations