© 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. 22-GEMMASCOPE-RES-131K
    4. 36586
    Prev
    Next
    INDEX
    Explanations

    what does it mean?

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

    This neuron detects occurrences of the “mean”/“matter” lexeme (e.g. English “mean” in “what does … mean?” or Russian “дело” in “в чем дело?”) in questions.

    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
     to
    -1.34
     But
    -1.22
    probably
    -1.16
    zaSy
    -1.16
     The
    -1.14
     of
    -1.13
     your
    -1.11
    >?
    -1.09
    marzo
    -1.09
     wesentlich
    -1.04
    POSITIVE LOGITS
    ?
    3.47
    ?”
    1.44
    domada
    1.41
    もありますが
    1.39
     Préférences
    1.37
    Preparazione
    1.30
    kulum
    1.28
     بیمارستان
    1.28
    もありました
    1.27
    不过是
    1.27
    Activations Density 0.064%

    No Known Activations