© 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. 124599
    Prev
    Next
    INDEX
    Explanations

    Hood, Live, space, Season, red, Service

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

    The neuron strongly activates on standalone content words that serve as section or heading titles (e.g. major nouns in titles or list 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
     Tentang
    -1.80
    detek
    -1.68
     zamiast
    -1.60
    gemeen
    -1.59
     we
    -1.59
     Jeden
    -1.59
     Terkait
    -1.59
    kenal
    -1.52
    ichtete
    -1.51
    pastebin
    -1.50
    POSITIVE LOGITS
     of
    1.88
     meningkatkan
    1.76
     a
    1.72
     behov
    1.64
     if
    1.63
    ud
    1.55
    ris
    1.53
    ra
    1.53
    tif
    1.53
     jiné
    1.52
    Activations Density 0.149%

    No Known Activations