© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93132
    Prev
    Next
    INDEX
    Explanations

    ^2

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

    The neuron fires on the LaTeX “^” exponent‐marker, i.e. it detects caret symbols used to indicate superscripts/exponents in math 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
    けどね
    -1.23
    などは
    -1.15
     ujarnya
    -1.13
     inconveniente
    -1.11
     dourada
    -1.09
    来到了
    -1.09
     gese
    -1.08
    萏
    -1.08
    仕上が
    -1.07
    鮰
    -1.07
    POSITIVE LOGITS
     and
    1.41
    ところに
    1.36
    WithString
    1.28
    messung
    1.27
     gevonden
    1.19
    ândia
    1.18
     toepassing
    1.18
     kecil
    1.14
     With
    1.13
     belangrij
    1.13
    Activations Density 0.011%

    No Known Activations