© 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. 22-GEMMASCOPE-RES-131K
    7. 98284
    Prev
    Next
    INDEX
    Explanations

    More followed by qualifiers

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

    The neuron consistently fires on the standalone token “More,” marking continuation or “read more” breaks in the text.

    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
    廰
    -2.20
    -
    -2.14
     suministros
    -2.14
     使っ
    -2.13
     sooo
    -2.11
    管家
    -2.09
     somewhat
    -2.09
    みたら
    -2.08
    翃
    -2.02
    zości
    -2.00
    POSITIVE LOGITS
     than
    4.06
    
    2.67
    媜
    2.61
    橚
    2.58
    When
    2.55
    They
    2.55
    Even
    2.45
    AutoresizingMask
    2.41
     Some
    2.39
    Before
    2.31
    Activations Density 0.107%

    No Known Activations