© 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. 22-GEMMASCOPE-RES-131K
    7. 70505
    Prev
    Next
    INDEX
    Explanations

    articles followed by descriptive word

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

    This neuron fires on tokens that appear in document metadata or structural elements—section headings, side‐bar titles, list labels, and numbered list items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    itisation
    -1.24
    brtc
    -1.22
    canActivate
    -1.20
    fikasi
    -1.19
     weißem
    -1.17
     Однако
    -1.15
    Однако
    -1.12
    满脸
    -1.11
     fakta
    -1.11
    zando
    -1.11
    POSITIVE LOGITS
     only
    1.49
     not
    1.49
     to
    1.45
    ないです
    1.37
     no
    1.31
     didn
    1.31
    chemise
    1.23
    ありません
    1.16
     “
    1.12
     just
    1.11
    Activations Density 0.001%

    No Known Activations