© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30048
    Prev
    Next
    INDEX
    Explanations

    mathematical questions and instructions

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

    The neuron consistently lights up on isolated mathematical symbols—especially numeric literals and single‐letter variables—used in algebraic or arithmetic expressions.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     praktis
    -1.17
    ֺ
    -1.10
     indeks
    -1.05
     kafe
    -1.05
     risiko
    -1.05
     plakat
    -1.05
     intelek
    -1.05
     kategor
    -1.02
     estancia
    -1.00
    䊊
    -0.99
    POSITIVE LOGITS
     questions
    1.15
     answer
    1.13
     unknown
    1.09
     MacBook
    1.05
     Write
    1.03
     Determine
    1.01
     Select
    1.00
     Show
    0.98
     Question
    0.98
     What
    0.97
    Activations Density 0.317%

    No Known Activations