© 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. 25662
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

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

    The neuron flags code‐style mathematical notation—especially exponentiation (the “**” operator) and other formula tokens (like “cosx”).

    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
     for
    -1.08
     how
    -1.05
     his
    -1.02
    Ưu
    -0.98
     Agenda
    -0.94
     ciała
    -0.93
    でしたか
    -0.92
    而成
    -0.90
     Biographie
    -0.90
    tablissements
    -0.89
    POSITIVE LOGITS
    ilever
    1.13
     bestehenden
    1.09
     ((!
    1.02
     nordrhein
    1.01
     são
    0.97
    🟡
    0.96
    牛仔
    0.96
     namorado
    0.96
     estructuras
    0.96
     simplemente
    0.96
    Activations Density 0.005%

    No Known Activations