© 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. 57580
    Prev
    Next
    INDEX
    Explanations

    types of bathrooms

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

    The neuron detects tokens that are numerical figures (digits) representing counts, measurements, or quantities.

    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
     mögen
    -0.78
    couvrir
    -0.73
    gpl
    -0.73
     hörte
    -0.72
     得到
    -0.71
     dipende
    -0.71
    ઢ
    -0.70
    kuji
    -0.69
     prodot
    -0.69
     pious
    -0.68
    POSITIVE LOGITS
     bathroom
    1.52
     powder
    1.51
     Powder
    1.38
     half
    1.36
    half
    1.35
    Powder
    1.33
    HALF
    1.26
    ハーフ
    1.24
     HALF
    1.24
    powder
    1.24
    Activations Density 0.010%

    No Known Activations