© 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. 104224
    Prev
    Next
    INDEX
    Explanations

    concepts and their functions

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

    The neuron fires on uncommon, specialized nouns or jargon (e.g. technical terms, product names, or other rare domain-specific words).

    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
    0
    -1.80
    b
    -1.77
     utafiti
    -1.61
    还得
    -1.54
    …”
    -1.53
    y
    -1.52
    f
    -1.51
    v
    -1.49
    h
    -1.46
    k
    -1.45
    POSITIVE LOGITS
    dacia
    1.73
     in
    1.72
     sebelum
    1.66
     "}";
    1.54
     will
    1.52
    TheReal
    1.45
    żdż
    1.45
     so
    1.41
    %;
    1.41
    skoda
    1.39
    Activations Density 0.420%

    No Known Activations