© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67302
    Prev
    Next
    INDEX
    Explanations

    vim commands and options

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

    This neuron fires on code snippets or configuration blocks, i.e. segments containing programming or script syntax.

    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
    semantics
    -1.55
    ></
    -1.41
    '
    -1.35
    rinology
    -1.27
    }),
    -1.25
    ContentAsync
    -1.23
    idental
    -1.21
    mathcal
    -1.20
    תו
    -1.19
    vature
    -1.16
    POSITIVE LOGITS
    чает
    1.37
    ֭
    1.33
    expiresIn
    1.31
     Aquí
    1.29
     alcanzó
    1.26
     nejen
    1.26
     revelou
    1.22
     всі
    1.19
    LoadScene
    1.19
     masculinos
    1.17
    Activations Density 0.095%

    No Known Activations