© 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. 22-GEMMASCOPE-RES-131K
    7. 72913
    Prev
    Next
    INDEX
    Explanations

    comparison and demonstratives

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find standalone numeric tokens (like years, counts, or 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_22/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
    bluza
    -1.02
    عرض
    -1.02
    ₱
    -1.00
    người
    -1.00
     każdym
    -0.98
    nós
    -0.98
     {$\
    -0.98
    voller
    -0.97
    ὓ
    -0.96
    Oneof
    -0.96
    POSITIVE LOGITS
     compared
    1.77
     this
    1.49
     that
    1.31
     compare
    1.27
     those
    1.15
     these
    1.11
    Compar
    1.09
     which
    1.08
     dibandingkan
    1.06
     compares
    1.05
    Activations Density 0.043%

    No Known Activations