© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31485
    Prev
    Next
    INDEX
    Explanations

    quantifiers followed by nouns

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

    The neuron detects indefinite quantifier and generalizing words that signal unspecified or non-numeric amounts (e.g. various, several, other, few, many).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    各类
    -1.11
    ὔ
    -1.09
     melding
    -1.03
     élas
    -1.03
    媒體
    -1.02
     konflik
    -1.02
     velmi
    -1.02
     verschiedenen
    -1.01
     rusa
    -1.01
     diferentes
    -1.00
    POSITIVE LOGITS
     similar
    1.36
     such
    1.35
     important
    1.18
     prominent
    1.16
     few
    1.16
     vital
    1.14
     matured
    1.05
     like
    1.05
     irrelevant
    1.01
     distinguished
    1.00
    Activations Density 0.092%

    No Known Activations