© 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. 22-GEMMASCOPE-RES-131K
    7. 16735
    Prev
    Next
    INDEX
    Explanations

    math and code elements

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

    This neuron detects the exponentiation operator (the “**” token) and its use in power 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    jadikan
    -1.17
    muñeca
    -1.17
     What
    -1.13
    yarakat
    -1.09
     pä
    -1.09
     Problemas
    -1.07
    camis
    -1.07
    rucks
    -1.07
    producción
    -1.05
    laient
    -1.05
    POSITIVE LOGITS
    tissa
    1.07
    ンの
    1.06
     среды
    1.06
     varandra
    1.05
    quine
    1.04
    phrine
    1.03
     altres
    1.01
     sommar
    1.01
     ögon
    1.01
     gynhyrchwyd
    1.00
    Activations Density 0.002%

    No Known Activations