© 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. 83164
    Prev
    Next
    INDEX
    Explanations

    dates and times ranges

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

    The neuron detects date-range tokens—words and numbers that mark when events run (e.g. “through,” month names, and numerals in date spans).

    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
     preserving
    -0.86
     although
    -0.86
     notable
    -0.85
    avista
    -0.85
     immediately
    -0.84
     genuinely
    -0.82
     any
    -0.82
     مؤ
    -0.81
    手数料
    -0.80
     noticeable
    -0.79
    POSITIVE LOGITS
    ন্
    0.96
    حتى
    0.86
     untill
    0.85
     beker
    0.85
    lieg
    0.84
     till
    0.82
    INESS
    0.82
     Arbit
    0.81
    ぐる
    0.81
    Till
    0.81
    Activations Density 0.033%

    No Known Activations