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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6861
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and calculations

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

    The neuron strongly responds to mathematical expressions and function-definition contexts (e.g. “f,” “function,” “domain,” “range,” numerical formulas).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADMIN
    0.84
    Administ
    0.84
    管理者
    0.84
     Bazaar
    0.79
    admins
    0.79
    FBSDKSettings
    0.79
     ಕೆಲಸ
    0.77
    ♻
    0.77
    让他
    0.77
     হলাম
    0.77
    POSITIVE LOGITS
     equations
    1.25
     equation
    1.13
     polynomials
    1.02
     algebraic
    0.97
     polynomial
    0.96
     Equations
    0.96
     
    0.95
     quotients
    0.95
     perturbation
    0.94
     Theorem
    0.94
    Activations Density 0.131%

    No Known Activations