© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32164
    Prev
    Next
    INDEX
    Explanations

    string formatting operators

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

    The neuron fires on code‐style syntax—especially punctuation like braces (“{”), dots (“.”), and format/template markers—i.e. it detects code fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    kevin
    -0.77
     войне
    -0.75
    又不
    -0.72
     детские
    -0.72
     grec
    -0.72
     Sio
    -0.70
    luke
    -0.70
     solicitó
    -0.70
     divulgação
    -0.69
    kna
    -0.69
    POSITIVE LOGITS
     format
    1.45
     Substituting
    1.41
     substituting
    1.40
     substitution
    1.35
     replace
    1.35
    Substituting
    1.35
     replacements
    1.34
     substitute
    1.30
    format
    1.30
    replace
    1.29
    Activations Density 0.014%

    No Known Activations