© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58577
    Prev
    Next
    INDEX
    Explanations

    essential for

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

    This neuron specializes in detecting numeric tokens and date-like digit sequences (e.g., standalone numbers and years).

    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
     our
    -1.02
     this
    -1.01
     many
    -0.94
     direkten
    -0.84
    História
    -0.83
    tividade
    -0.83
     AGENCIES
    -0.83
     speziell
    -0.81
    erli
    -0.79
     cetak
    -0.78
    POSITIVE LOGITS
     interag
    0.98
    Tuesday
    0.91
     ส์
    0.86
    mögens
    0.85
     Арме
    0.84
    lining
    0.83
    lení
    0.82
    arted
    0.82
     RAC
    0.81
    CUT
    0.81
    Activations Density 0.006%

    No Known Activations