© 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. 34-GEMMASCOPE-RES-131K
    7. 94253
    Prev
    Next
    INDEX
    Explanations

    maybe, perhaps, uncertainty

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

    The neuron strongly activates on numerical expressions (digits and number words) in the text.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    有不少
    -0.88
    roscope
    -0.85
    Einige
    -0.85
     varias
    -0.84
    +#+
    -0.83
     Several
    -0.81
    +:+
    -0.79
     زود
    -0.79
     excellent
    -0.78
     nhiều
    -0.77
    POSITIVE LOGITS
     maybe
    3.97
    maybe
    3.34
    Maybe
    3.16
     Maybe
    2.80
     vielleicht
    2.67
     talvez
    2.42
     misschien
    2.36
     شاید
    2.25
     perhaps
    2.08
     belki
    1.99
    Activations Density 0.053%

    No Known Activations