© 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. 103234
    Prev
    Next
    INDEX
    Explanations

    variable dimensions and counts

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

    The neuron primarily activates on numeric literal tokens (integer constants) 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_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
     until
    -0.98
    tahu
    -0.95
    緞
    -0.90
     newly
    -0.89
     fået
    -0.89
     our
    -0.88
    DOCX
    -0.88
     Kälte
    -0.87
     till
    -0.87
     only
    -0.87
    POSITIVE LOGITS
    hips
    0.89
     chacun
    0.88
    fied
    0.88
    それぞれの
    0.87
    nels
    0.86
    alable
    0.83
    titu
    0.82
    因此
    0.81
    itatea
    0.81
    一个个
    0.81
    Activations Density 0.008%

    No Known Activations