© 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. 10-GEMMASCOPE-RES-131K
    7. 83919
    Prev
    Next
    INDEX
    Explanations

    X11 or x1 sequences

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

    The neuron strongly activates on the digit “1” token wherever it appears.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ”,
    -2.61
     possesses
    -2.55
     gratuito
    -2.41
    他是
    -2.36
     and
    -2.34
     accedi
    -2.31
    );
    -2.30
     you
    -2.25
     incorporates
    -2.22
     includes
    -2.17
    POSITIVE LOGITS
    ⬮
    2.53
     newfound
    2.44
     standout
    2.42
     bedeutend
    2.33
    Tä
    2.30
     Besonder
    2.28
     \"
    2.16
     gefährlich
    2.06
    蓴
    2.03
     responsables
    1.99
    Activations Density 0.026%

    No Known Activations