© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 3645
    Prev
    Next
    INDEX
    Explanations

    printing and logging output

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

    The neuron fires on numeric literal tokens (integer or floating‐point constants) in code snippets.

    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
     diku
    -1.12
    すみません
    -1.06
    はコチラ
    -1.05
     memili
    -1.02
    ifte
    -1.02
    にしました
    -1.01
     onlar
    -1.01
    While
    -0.99
    ㄚ
    -0.98
    **
    -0.97
    POSITIVE LOGITS
    ----------------
    1.56
     also
    1.21
    ****************
    1.01
    ================
    0.95
    p
    0.94
    gh
    0.94
     "
    0.91
    teel
    0.86
    ↵↵↵↵
    0.85
    ();
    0.85
    Activations Density 0.008%

    No Known Activations