© 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. 10-GEMMASCOPE-RES-131K
    7. 73019
    Prev
    Next
    INDEX
    Explanations

    pigment cells and genes

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

    references to pigments in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently activates on occurrences of the term “pigment” (and its variants) 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_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
    硨
    -2.66
    ?”
    -2.56
    an
    -2.53
    栊
    -2.48
    al
    -2.47
    嗵
    -2.38
    The
    -2.30
    蹀
    -2.28
     руке
    -2.25
    ){
    -2.23
    POSITIVE LOGITS
    鲠
    2.31
    渽
    2.27
     เพราะ
    2.27
     of
    2.25
    浔
    2.25
     lidé
    2.14
    洄
    2.14
    geſ
    2.13
    </em>
    2.13
    冏
    2.09
    Activations Density 0.009%

    No Known Activations