© 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. 59329
    Prev
    Next
    INDEX
    Explanations

    sweep and variations

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

    The neuron flags tokens that occur frequently within the same document (i.e. it activates on high in-doc term frequency).

    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
    srand
    -0.82
    getRandom
    -0.81
    hướng
    -0.77
    هور
    -0.77
    gın
    -0.75
    стандарт
    -0.73
    lossen
    -0.73
     hashlib
    -0.72
     най
    -0.71
    اصله
    -0.71
    POSITIVE LOGITS
     sweep
    4.97
    sweep
    4.09
     sweeps
    4.03
     swept
    4.00
     Sweep
    3.95
    Sweep
    3.77
     sweeping
    3.48
    swept
    3.02
    swe
    2.34
    Swe
    2.28
    Activations Density 0.039%

    No Known Activations