© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83217
    Prev
    Next
    INDEX
    Explanations

    -00:00 time offsets

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

    The neuron fires on dash (“‐”) tokens used as minus signs or separators in numeric contexts—e.g. in dates, version numbers, ranges, and other numeral‐linked hyphens.

    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
     those
    -1.20
     issues
    -1.02
     (+
    -0.84
    icke
    -0.84
     тоже
    -0.84
    Those
    -0.84
     celui
    -0.77
     issue
    -0.77
     тот
    -0.75
    その
    -0.74
    POSITIVE LOGITS
    webkit
    1.14
    ˏ
    0.98
     créées
    0.93
    =-=-
    0.91
     garan
    0.89
     mivel
    0.89
    lencia
    0.88
    ">-
    0.85
    sieren
    0.84
    這樣的
    0.84
    Activations Density 0.129%

    No Known Activations