© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64298
    Prev
    Next
    INDEX
    Explanations

    other

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

    The neuron responds to numeric quantifiers—cardinal numbers (e.g. “five,” “nine,” “six”) and related words (“other,” “additional,” “further”) that indicate counts of items.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     zarówno
    -1.09
     outing
    -0.96
    كثر
    -0.92
    ﻹ
    -0.87
     われ
    -0.86
    bagai
    -0.85
     nawet
    -0.85
     both
    -0.85
    onnage
    -0.85
    chenden
    -0.84
    POSITIVE LOGITS
     other
    3.55
     others
    2.50
    其他
    2.42
     lainnya
    2.20
     autres
    2.17
     دیگر
    2.11
     других
    2.11
     otras
    2.09
     andere
    2.09
     otros
    2.09
    Activations Density 0.041%

    No Known Activations