© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    brown color descriptor

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

    This neuron specifically activates on occurrences of the color term “brown.”

    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
     The
    -2.31
    のおかげ
    -2.14
    十足
    -2.14
    ?”
    -2.11
     Pokud
    -2.09
     Jeśli
    -2.09
     involucrados
    -2.09
     cihaz
    -2.02
     стоимость
    -1.99
    甃
    -1.98
    POSITIVE LOGITS
     \&
    2.48
    ،
    2.44
     весна
    2.44
    -
    2.42
    随后
    2.27
    ！】
    2.27
     és
    2.25
    榈
    2.23
     excessively
    2.20
    стреча
    2.19
    Activations Density 0.006%

    No Known Activations