© 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. 10-GEMMASCOPE-RES-131K
    4. 61407
    Prev
    Next
    INDEX
    Explanations

    links followed by names

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

    This neuron activates on the hyphen used as a separator (e.g. in “Title – Author/Year”) in list‐item headings.

    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
    in
    -2.69
    is
    -2.05
    who
    -1.66
     може
    -1.66
    man
    -1.66
     basé
    -1.60
    早就
    -1.58
     eject
    -1.51
    сти
    -1.48
    na
    -1.47
    POSITIVE LOGITS
     uſed
    2.08
    臯
    2.03
    眥
    1.94
    KommentareTeilen
    1.92
    تیجه
    1.91
    了一种
    1.91
     wollten
    1.88
    งิน
    1.87
     have
    1.86
    寕
    1.86
    Activations Density 0.017%

    No Known Activations