© 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. 47284
    Prev
    Next
    INDEX
    Explanations

    UI popup or activity indicator

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

    The neuron is primarily triggered by numeric literals (digits and numbers) 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
     прото
    -0.84
     OnTriggerEnter
    -0.77
    wasm
    -0.75
    oo
    -0.74
     preis
    -0.74
     tilf
    -0.73
     الرجل
    -0.71
    matics
    -0.70
    ssh
    -0.69
    体内
    -0.68
    POSITIVE LOGITS
    Hud
    1.38
     hud
    1.30
     Hud
    1.24
    hud
    1.18
    HUD
    1.16
     HUD
    1.15
    MB
    1.06
     MB
    0.90
    SV
    0.87
     SV
    0.79
    Activations Density 0.009%

    No Known Activations