© 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. 63448
    Prev
    Next
    INDEX
    Explanations

    Islam, Pakistan, American

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

    The neuron is tuned to spotting numeric tokens (years, dates, and other numbers).

    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
     can
    -0.81
     cues
    -0.81
     didn
    -0.80
     *
    -0.79
    原生
    -0.75
     skillet
    -0.72
     política
    -0.71
     casi
    -0.70
     /
    -0.70
     if
    -0.70
    POSITIVE LOGITS
     Promised
    0.98
     MTA
    0.95
     Ah
    0.95
     Maud
    0.93
    Ah
    0.90
     svol
    0.89
     subtil
    0.89
     AMOR
    0.87
     RECOM
    0.86
     koi
    0.86
    Activations Density 0.004%

    No Known Activations