© 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. 105135
    Prev
    Next
    INDEX
    Explanations

    string formatting placeholders

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

    string formatting placeholders in code, particularly `{0}` and similar numeric format specifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on numeric literals (sequences of digits, possibly with decimals) in code or 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
     chini
    -1.48
    e
    -1.32
    );
    -1.32
    ).
    -1.30
     kwamba
    -1.21
     annen
    -1.20
    I
    -1.13
    empio
    -1.12
    ..)
    -1.11
     laat
    -1.10
    POSITIVE LOGITS
     historiador
    1.35
    commande
    1.35
     stanov
    1.34
    otriva
    1.34
     Sección
    1.34
    typeout
    1.33
    valg
    1.31
    Karriere
    1.28
    hoodie
    1.28
     Brasileira
    1.27
    Activations Density 0.024%

    No Known Activations