© 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. 32929
    Prev
    Next
    INDEX
    Explanations

    locations, genres, and data types

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

    The main thing this neuron does is detect numeric tokens (sequences of digits, including multi-digit numbers and decimal values).

    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
    although
    -1.00
    ∵
    -0.91
     Descargar
    -0.88
    ఱ
    -0.88
    ⚫
    -0.88
    流れる
    -0.85
    endiente
    -0.85
     halves
    -0.85
    这几
    -0.85
    不堪
    -0.84
    POSITIVE LOGITS
     secondary
    0.83
    psie
    0.82
    usel
    0.81
     specialize
    0.80
    raim
    0.80
     tarvit
    0.79
     frequentemente
    0.79
     situada
    0.78
     использованием
    0.78
     milhões
    0.78
    Activations Density 0.256%

    No Known Activations