© 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. 124076
    Prev
    Next
    INDEX
    Explanations

    promoter motifs, regions, complexes

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

    The neuron detects the word "promoter" in scientific texts, particularly when discussing gene regulation and transcription.

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

    The neuron is detecting mentions of “promoter” (and closely related promoter-motif/configuration terms) in biological 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
    of
    -2.67
    떳
    -2.31
     taką
    -2.27
    s
    -2.20
     ‚
    -2.19
    lawesi
    -2.16
     the
    -2.14
    秾
    -2.13
     amantes
    -2.06
    wiście
    -2.06
    POSITIVE LOGITS
    '
    3.38
    \
    3.05
    <i>
    2.61
            
    2.52
    ⣉
    2.45
     We
    2.34
    ÍTULO
    2.20
    t
    2.14
    ～。
    2.09
    ции
    2.08
    Activations Density 0.004%

    No Known Activations