© 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. 120123
    Prev
    Next
    INDEX
    Explanations

    big/little concepts

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

    This neuron highlights relatively rare, content-rich words (i.e. words with high inverse document frequency) rather than common function 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
     as
    -2.13
     both
    -1.68
     or
    -1.55
     również
    -1.55
     by
    -1.45
     its
    -1.34
     on
    -1.33
    蜗
    -1.32
     arī
    -1.30
     either
    -1.23
    POSITIVE LOGITS
    なぜ
    1.46
    次は
    1.41
    />";
    1.41
     />";
    1.38
     těch
    1.37
     obyvateľov
    1.34
     beſt
    1.34
    なんとなく
    1.34
    /";
    1.33
     lefs
    1.33
    Activations Density 0.104%

    No Known Activations