© 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. 11070
    Prev
    Next
    INDEX
    Explanations

    evolutionary biology

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

    The neuron detects the word "evolutionary" in scientific and technical contexts.

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

    The neuron consistently activates on occurrences of the word “evolutionary.”

    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
    -2.98
    瘰
    -2.53
     trozos
    -2.50
     Если
    -2.44
    ਃ
    -2.36
    \
    -2.31
    ⴽ
    -2.28
     involucrados
    -2.25
     berharap
    -2.20
     dientes
    -2.19
    POSITIVE LOGITS
    <
    3.16
    that
    2.59
    ,’
    2.58
    _
    2.52
     harmonious
    2.42
    縯
    2.42
    The
    2.41
    re
    2.39
     unsere
    2.38
    <i>
    2.34
    Activations Density 0.003%

    No Known Activations