© 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. 64011
    Prev
    Next
    INDEX
    Explanations

    mortuary affairs and death education

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

    The neuron strongly activates on numeric tokens (digits, years, counts) 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
     excit
    -0.79
    };*/
    -0.79
     feeders
    -0.79
     Infer
    -0.78
    好评
    -0.77
     killed
    -0.77
     Nuk
    -0.76
    infer
    -0.75
    orphism
    -0.75
     подключения
    -0.74
    POSITIVE LOGITS
     embal
    0.84
    ilosop
    0.84
     families
    0.83
     Dignity
    0.80
     funeral
    0.77
    äv
    0.77
     선택
    0.77
     gọi
    0.76
    Wm
    0.75
    embal
    0.75
    Activations Density 0.007%

    No Known Activations