© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99911
    Prev
    Next
    INDEX
    Explanations

    assembly code and batch scripts

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

    The neuron fires on numeric literals (stand-alone numbers) in code or assembly instructions.

    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
     including
    -0.99
     muualla
    -0.88
     their
    -0.86
     rezept
    -0.83
     esimerkiksi
    -0.83
     {
    -0.81
     medan
    -0.81
    Rüyada
    -0.80
    imread
    -0.78
    /*++
    -0.77
    POSITIVE LOGITS
     assignee
    0.89
    Viernes
    0.89
    lė
    0.84
     сотруд
    0.82
    //}
    0.81
     Marry
    0.80
    João
    0.78
     результат
    0.77
    Poh
    0.77
     bağlantılar
    0.76
    Activations Density 0.003%

    No Known Activations