© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33948
    Prev
    Next
    INDEX
    Explanations

    intervals and breaks

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

    The neuron fires on mentions of periods of time (e.g. “free time,” “spare time,” “half-time,” “recess”).

    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
     duplicates
    -0.90
     váll
    -0.86
    bena
    -0.86
     szükség
    -0.85
     biztons
    -0.84
    ıkları
    -0.84
    bair
    -0.84
     jöv
    -0.84
    volkswagen
    -0.84
     جديدة
    -0.83
    POSITIVE LOGITS
    unduh
    1.02
    between
    0.98
     antics
    0.94
     cadre
    0.92
     proced
    0.91
     Hanging
    0.90
     méri
    0.89
     между
    0.88
     time
    0.87
     between
    0.86
    Activations Density 0.057%

    No Known Activations