© 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. 40048
    Prev
    Next
    INDEX
    Explanations

    quantifiers followed by categories

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

    the neuron detects non‐specific quantity words or plural descriptors (e.g. “several,” “numerous,” “various,” “many,” “other,” “features”).

    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
     because
    -1.34
    ѧ
    -1.21
    ddling
    -1.18
    itting
    -1.16
    我真的
    -1.14
    affaires
    -1.13
    fordshire
    -1.10
    民眾
    -1.07
     funzionamento
    -1.05
     where
    -1.04
    POSITIVE LOGITS
     such
    1.20
     safety
    1.16
     like
    1.16
    如
    1.14
    он
    1.14
     जैसे
    1.13
     egyéb
    1.08
     also
    1.01
    包括
    0.95
     özellikleri
    0.93
    Activations Density 0.095%

    No Known Activations