© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72726
    Prev
    Next
    INDEX
    Explanations

    all

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

    The neuron fires on the universal-quantifier “all” (and the items it scopes over, e.g. “all CDHP enrollees,” “all apps,” “for all diesel engines,” etc.).

    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
     chao
    -1.28
     conflic
    -1.23
     sufic
    -1.20
     コンパクト
    -1.20
    zystać
    -1.20
     acca
    -1.20
     brillant
    -1.18
     العلاج
    -1.16
     previos
    -1.15
     prohi
    -1.15
    POSITIVE LOGITS
     December
    1.46
     October
    1.29
     September
    1.27
     after
    1.26
    </h3>
    1.25
     January
    1.21
     any
    1.20
     that
    1.18
     in
    1.18
     February
    1.16
    Activations Density 0.157%

    No Known Activations