© 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. 10-GEMMASCOPE-RES-131K
    7. 87370
    Prev
    Next
    INDEX
    Explanations

    series followed by comma

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

    The neuron specializes in detecting ellipsis markers (e.g. the “\ldots” token) that indicate omitted content.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     If
    -2.73
     принад
    -2.17
    りは
    -2.13
     devotees
    -2.11
    bidities
    -2.09
    攻擊
    -2.06
    讴
    -2.05
     [];
    -2.03
     către
    -2.02
    (!__
    -1.98
    POSITIVE LOGITS
    ldots
    2.98
    a
    2.67
    ’
    2.61
    Ꮴ
    2.56
    咴
    2.53
    ↵
    2.41
    ing
    2.39
    蒞
    2.31
    lies
    2.19
    ,.
    2.19
    Activations Density 0.002%

    No Known Activations