© 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. 67985
    Prev
    Next
    INDEX
    Explanations

    code comparison and blocks

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

    The neuron identifies numeric literals (e.g. integers, floats, version numbers, counts) in code and markup.

    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
    着一个
    -1.20
    ourced
    -1.18
     նաև
    -1.11
     Sélectionnez
    -1.09
     ТАК
    -1.09
    jenige
    -1.07
     Дмитрий
    -1.05
    thentication
    -1.05
    золо
    -1.05
     another
    -1.04
    POSITIVE LOGITS
    ↵↵
    1.79
    这些
    1.40
     altijd
    1.30
    これらの
    1.19
     what
    1.19
    這些
    1.16
     respectivamente
    1.12
    必须
    1.11
     şeyi
    1.10
    <eos>
    1.05
    Activations Density 0.002%

    No Known Activations