© 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. 59303
    Prev
    Next
    INDEX
    Explanations

    indoor environments and locations

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

    The main thing this neuron does is detect the word “indoor” (i.e. references to indoor spaces or contexts).

    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
    '
    -3.88
    轫
    -2.38
     عندما
    -2.22
     I
    -2.17
    可能会
    -2.03
    geſ
    -2.03
     zumal
    -2.02
     slap
    -1.95
     kirj
    -1.94
    {~
    -1.92
    POSITIVE LOGITS
    再来
    2.81
    with
    2.73
    ⬮
    2.63
    𓆜
    2.33
    ஂ
    2.30
    櫺
    2.28
    Bahkan
    2.20
    　(
    2.16
     ；
    2.14
    鮓
    2.14
    Activations Density 0.007%

    No Known Activations