© 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. 22-GEMMASCOPE-RES-131K
    4. 84019
    Prev
    Next
    INDEX
    Explanations

    explaining with "that's"

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

    The neuron fires on emphatic or intensifying markers—numbers, elongated punctuation (e.g. “....”), and words of sudden or total change (e.g. “all,” “sudden,” “you”)—that signal strong emphasis.

    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
    yecek
    -0.99
     izany
    -0.93
    แสดง
    -0.92
    場合があります
    -0.91
     koniecz
    -0.90
     powy
    -0.89
     here
    -0.86
    currentValue
    -0.84
    ématiques
    -0.84
    onacci
    -0.84
    POSITIVE LOGITS
    最新
    1.08
    '>
    
    1.00
    gments
    0.94
    由
    0.94
    但
    0.93
     being
    0.93
    )]=
    0.92
    ため
    0.88
    ךְ
    0.86
    except
    0.85
    Activations Density 0.031%

    No Known Activations