© 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. 30208
    Prev
    Next
    INDEX
    Explanations

    "By", "title", "Locations"

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

    The neuron activates strongly on numeric tokens and numeric sequences (e.g. digits in prices, model numbers, versions, dates).

    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
     celebridades
    -0.79
     Experts
    -0.75
     Mobil
    -0.75
    fame
    -0.73
     fucking
    -0.72
    suri
    -0.71
     Peng
    -0.70
    titut
    -0.70
    infile
    -0.70
     shit
    -0.69
    POSITIVE LOGITS
    referenced
    0.76
     недо
    0.74
    tellingen
    0.73
     Metroid
    0.72
    rzez
    0.71
    Env
    0.69
     Partagez
    0.69
    Ǟ
    0.69
    現在
    0.68
    letzt
    0.67
    Activations Density 0.008%

    No Known Activations