© 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. 73011
    Prev
    Next
    INDEX
    Explanations

    mathematical variables, code comments, question markers, formal documents

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

    This neuron activates on the standalone character “k,” typically when it appears as a variable or constant in mathematical expressions.

    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
     ヘ
    -1.16
     Şubat
    -1.08
    ｓ
    -1.05
     domingos
    -1.04
    plakat
    -1.04
    }};
    -1.04
    loggen
    -1.03
     boletos
    -1.01
     моих
    -1.01
    xmlhttp
    -1.01
    POSITIVE LOGITS
     препарат
    1.24
     새로운
    1.21
    analog
    1.20
    虽说
    1.14
     голова
    1.13
    了些
    1.09
     neque
    1.07
    lesssim
    1.07
     현재
    1.07
    zyms
    1.06
    Activations Density 0.000%

    No Known Activations