© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41180
    Prev
    Next
    INDEX
    Explanations

    expressions with punctuation and numbers

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

    The neuron fires on instances of the “**” exponent‐iation operator (i.e. power notation) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    냑
    -1.45
    깽
    -1.43
     estreia
    -1.37
    洗い
    -1.31
    鹟
    -1.29
    懨
    -1.29
     добраться
    -1.27
     increíble
    -1.27
    ecution
    -1.26
     conhecer
    -1.23
    POSITIVE LOGITS
    需要
    1.34
    常常
    1.17
     is
    1.14
    romantic
    1.13
     चाहता
    1.11
     where
    1.07
    Porque
    1.07
    ’
    1.05
     autres
    1.04
    情况
    1.04
    Activations Density 0.055%

    No Known Activations