© 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. 9821
    Prev
    Next
    INDEX
    Explanations

    CGRectMake or dimensions

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

    The neuron is picking out numeric literals (standalone numbers) 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
     that
    -1.22
    <bos>
    -1.20
    齟
    -1.17
    軋
    -1.12
     those
    -1.12
    .《
    -1.11
     rodríguez
    -1.09
     sánchez
    -1.09
     Songtext
    -1.08
     €,
    -1.08
    POSITIVE LOGITS
     nossa
    1.18
    錆
    1.15
     гораздо
    1.10
     великолеп
    1.09
     nosso
    1.09
    ピッタリ
    1.09
    へ向
    1.09
    シャレ
    1.08
     nossas
    1.07
     источник
    1.05
    Activations Density 0.004%

    No Known Activations