© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128585
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically detects the “More <num>” continuation markers (the word “More” followed by a digit token) that signal truncated content.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     other
    -1.31
     otros
    -1.29
     zove
    -1.20
    Тарих
    -1.19
    =='
    -1.19
     nasled
    -1.17
    찻
    -1.16
    また
    -1.16
    ATIVE
    -1.14
     TextAppearance
    -1.14
    POSITIVE LOGITS
     than
    1.53
    _
    1.40
     is
    1.28
     importantly
    1.25
    ing
    1.18
    They
    1.17
    する方法
    1.14
    .
    1.11
     zůst
    1.11
    はこちらから
    1.11
    Activations Density 0.032%

    No Known Activations