© 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. 19269
    Prev
    Next
    INDEX
    Explanations

    uncertainty and unknowns

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

    The neuron fires on specialized, low-frequency technical or academic content words (e.g. domain-specific nouns and formal discourse terms).

    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
     like
    -1.55
     could
    -1.54
     and
    -1.50
     should
    -1.48
     with
    -1.45
     without
    -1.37
     /
    -1.34
    !
    -1.34
    !!
    -1.31
     might
    -1.30
    POSITIVE LOGITS
     its
    2.42
    皷
    1.50
     bourg
    1.50
     Règlement
    1.43
     péro
    1.41
     vinyle
    1.39
     própri
    1.38
     sén
    1.34
    itself
    1.34
     Wikipédia
    1.34
    Activations Density 0.433%

    No Known Activations