© 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. 102001
    Prev
    Next
    INDEX
    Explanations

    polypeptide and acetone

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

    The neuron detects the word "polypeptide" and related biochemical terms like "acetone".

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

    The neuron flags scientific substance or molecule names immediately followed by numeric measurements (especially decimals), e.g. “polypeptide 136,” “acetone 98.5,” etc.

    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
    and
    -2.44
     biblia
    -2.41
    ↵↵
    -2.34
    掂
    -2.31
    （
    -2.17
    を
    -2.16
    、
    -2.11
     vuole
    -2.09
    蠓
    -2.06
     și
    -2.03
    POSITIVE LOGITS
    ’.
    3.09
    ↵
    2.72
    ’:
    2.55
    ’,
    2.55
    s
    2.44
    .’
    2.30
    ,’
    2.22
     なお
    2.16
     ‘
    2.14
    section
    2.08
    Activations Density 0.008%

    No Known Activations