© 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. 50310
    Prev
    Next
    INDEX
    Explanations

    official statistics

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

    This neuron detects occurrences of the word “statistic(s)” (including its abbreviations like “stats”) or similar statistical section headings.

    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
    先是
    -1.07
    各有
    -1.02
    SETTING
    -0.98
     devout
    -0.95
     hark
    -0.93
    Marke
    -0.91
    Loud
    -0.91
     slated
    -0.90
    Lom
    -0.90
     Appreciate
    -0.89
    POSITIVE LOGITS
    Stat
    1.36
    tics
    1.31
     Stat
    1.27
     STAT
    1.16
    stat
    1.13
     stat
    1.10
    ical
    1.03
    показа
    1.02
     ModelAndView
    1.02
     €)
    1.00
    Activations Density 0.011%

    No Known Activations