© 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. 16239
    Prev
    Next
    INDEX
    Explanations

    the second derivative

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

    The neuron fires on highly technical mathematical notation—variables, symbols, formula parts, and equation-style tokens.

    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
     sostenibilidad
    -1.11
     concetto
    -1.11
     a
    -1.03
     largely
    -1.02
     ము
    -1.00
    brd
    -0.99
     never
    -0.99
     kauf
    -0.97
     Anges
    -0.96
    ampiyon
    -0.95
    POSITIVE LOGITS
     from
    1.65
     with
    1.23
    ΑΡ
    1.16
     when
    1.11
     akci
    1.10
     autonomie
    1.09
    ༼
    1.09
     that
    1.09
    ヾ
    1.09
     if
    1.07
    Activations Density 0.038%

    No Known Activations