© 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. 104891
    Prev
    Next
    INDEX
    Explanations

    from here or there

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

    This neuron activates on discourse-marker phrases that point to a location or continuation in the text—especially “here” and “from here/on(ward),” and similarly “there” in “from there,” marking where the discussion continues.

    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
    涐
    -2.09
     Japão
    -2.00
     ドール
    -1.99
    ↵↵
    -1.96
    ܜ
    -1.83
    Ꮅ
    -1.82
    jangkau
    -1.82
     móviles
    -1.81
    绻
    -1.78
    儼
    -1.77
    POSITIVE LOGITS
    z
    2.55
    in
    2.27
    ;
    2.06
    鸶
    2.06
    .
    2.05
    m
    1.92
    ve
    1.91
    res
    1.91
    he
    1.89
     start
    1.89
    Activations Density 0.003%

    No Known Activations