© 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. 34-GEMMASCOPE-RES-131K
    7. 4309
    Prev
    Next
    INDEX
    Explanations

    language codes like en

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

    The neuron fires on numeric literals and their surrounding key‐value tokens (e.g. parameter names, equals signs, or other assignment contexts).

    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
    شرين
    -0.72
    صاص
    -0.70
    ຶ
    -0.66
     broiler
    -0.66
     као
    -0.66
    vermectin
    -0.66
    iga
    -0.65
     modific
    -0.63
    switchTo
    -0.63
    Willing
    -0.63
    POSITIVE LOGITS
    祢
    0.69
     village
    0.68
     cocked
    0.66
     SIMBAD
    0.65
     plaat
    0.63
    翻訳
    0.63
    VIR
    0.62
     SYDNEY
    0.62
    wira
    0.62
    まま
    0.62
    Activations Density 0.060%

    No Known Activations