© 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. 69231
    Prev
    Next
    INDEX
    Explanations

    each of

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

    The neuron activates on general-quantity words (indefinite quantifiers) such as “many,” “some,” “each,” and “all.”

    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
     hábit
    -1.33
     cualidades
    -1.30
     esfuer
    -1.30
     sensaciones
    -1.28
     hermosas
    -1.25
     campañas
    -1.23
     everything
    -1.22
    ➓
    -1.22
     komfort
    -1.21
     various
    -1.20
    POSITIVE LOGITS
     which
    2.56
     of
    2.08
     with
    1.92
     которых
    1.54
    which
    1.52
    ซึ่ง
    1.34
    GRAFÍA
    1.26
     denen
    1.24
     from
    1.23
    hich
    1.21
    Activations Density 0.038%

    No Known Activations