© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95347
    Prev
    Next
    INDEX
    Explanations

    string formatting specifiers

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

    The neuron is keyed to spotting string formatting directives (e.g. “%s”, “%d”, “~A”, etc.) in code.

    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
    mitsub
    -1.65
    kenzo
    -1.62
     those
    -1.59
     this
    -1.58
     both
    -1.55
    conhe
    -1.50
     extraña
    -1.47
     various
    -1.43
    fokus
    -1.43
     zra
    -1.38
    POSITIVE LOGITS
    _
    1.63
    </strong>
    1.41
    l
    1.23
    X
    1.23
    w
    1.22
    J
    1.18
    S
    1.17
    ou
    1.16
    ve
    1.15
    h
    1.14
    Activations Density 0.004%

    No Known Activations