© 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. 34-GEMMASCOPE-RES-131K
    7. 102899
    Prev
    Next
    INDEX
    Explanations

    household waste disposal

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

    This neuron specializes in detecting numeric information such as dates, times, quantities, and other number‐related tokens.

    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
    ET
    -0.85
    andt
    -0.84
    ниці
    -0.77
    aurus
    -0.76
    stasis
    -0.75
    fontSize
    -0.73
     nephews
    -0.73
    Ta
    -0.73
    ēju
    -0.73
    RO
    -0.73
    POSITIVE LOGITS
     residents
    1.16
     Household
    1.12
     household
    1.11
    accepted
    1.09
    Household
    1.07
     Accepted
    1.03
    household
    1.02
     accepted
    0.98
     Residents
    0.98
    Residents
    0.97
    Activations Density 0.018%

    No Known Activations