© 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. 64446
    Prev
    Next
    INDEX
    Explanations

    recursive-include distributed *.html

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

    The neuron activates primarily on numeric tokens (i.e., numbers and number‐like strings).

    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
     feitas
    -1.26
     espectadores
    -1.24
     soldados
    -1.23
     écl
    -1.20
     aussitôt
    -1.20
     obé
    -1.19
     hadden
    -1.18
    Är
    -1.16
     récla
    -1.15
     burbujas
    -1.15
    POSITIVE LOGITS
     for
    1.29
     etc
    1.11
     to
    1.07
     lastly
    1.02
     although
    1.02
     –
    1.02
    …？
    1.01
     ....
    0.99
    …..
    0.99
     until
    0.98
    Activations Density 0.006%

    No Known Activations