© 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. 30186
    Prev
    Next
    INDEX
    Explanations

    reported on, Appeals of

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

    The neuron primarily responds to numeric tokens (digits and multi‐digit numbers), such as reference indices, dates, codes, and other numerical sequences.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Norman
    -0.70
    omin
    -0.69
     stormed
    -0.67
    assurer
    -0.66
     Sevilla
    -0.66
     Morning
    -0.65
     possui
    -0.65
    umin
    -0.65
    SW
    -0.64
    
    -0.64
    POSITIVE LOGITS
    {*
    0.73
    ilización
    0.69
     demographics
    0.65
     troppo
    0.64
    обра
    0.64
     berat
    0.63
    alini
    0.63
     reich
    0.63
     flag
    0.63
    ichia
    0.63
    Activations Density 0.054%

    No Known Activations