© 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. 10-GEMMASCOPE-RES-131K
    7. 14458
    Prev
    Next
    INDEX
    Explanations

    burning descriptor

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

    The neuron specifically detects occurrences of the word “burning.”

    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
    {
    -3.47
    k
    -3.34
    p
    -2.92
     skrev
    -2.91
    j
    -2.89
    s
    -2.86
    z
    -2.83
    ot
    -2.83
    ad
    -2.80
    ar
    -2.67
    POSITIVE LOGITS
     That
    2.98
    unjung
    2.75
    轫
    2.70
     of
    2.66
     большая
    2.63
    趼
    2.63
    selbe
    2.58
    стреча
    2.56
    鲀
    2.55
    剽
    2.53
    Activations Density 0.003%

    No Known Activations