© 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. 22-GEMMASCOPE-RES-131K
    7. 469
    Prev
    Next
    INDEX
    Explanations

    any, everything, anything

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

    The neuron fires primarily on universal or indefinite quantifier words (e.g. “anyone,” “everything,” “anything,” “every,” “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
     loto
    -1.17
     kablo
    -1.17
     porno
    -1.09
     entièrement
    -1.08
     papy
    -1.03
    lasyon
    -1.02
    整體
    -1.02
     morm
    -1.02
    tely
    -1.02
    整体
    -1.02
    POSITIVE LOGITS
     imaginable
    1.71
     possible
    1.48
     available
    1.45
     conceivable
    1.42
     including
    1.41
     وكل
    1.23
     anything
    1.23
     cualquier
    1.20
     posibles
    1.16
     moindre
    1.10
    Activations Density 0.031%

    No Known Activations