© 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. 22-GEMMASCOPE-RES-131K
    7. 66765
    Prev
    Next
    INDEX
    Explanations

    amino acid substitutions or mutations

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

    genetic mutation codes in scientific texts, particularly amino acid substitutions represented by numbers and letters.

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

    The neuron activates on tokens that are numerical or contain digit sequences (i.e. numbers or numeric identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sereia
    -1.41
    columnHeader
    -1.29
     правительства
    -1.27
     étr
    -1.23
     defStyle
    -1.16
     regreso
    -1.16
     sapat
    -1.16
    
    -1.15
     aseguró
    -1.14
    plakat
    -1.14
    POSITIVE LOGITS
     in
    1.28
    (
    1.27
     (
    1.25
     
    1.17
    n
    1.09
    ;
    1.08
    :
    1.07
    …
    1.05
    )
    1.04
     because
    1.03
    Activations Density 0.040%

    No Known Activations