© 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. 16135
    Prev
    Next
    INDEX
    Explanations

    closing braces and `endif`

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

    The neuron is detecting deeply indented lines (i.e. sequences of leading spaces or tabs) in code.

    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
    ventes
    -1.31
     klinik
    -1.31
     berken
    -1.30
     belga
    -1.25
     parfü
    -1.22
     parfüm
    -1.22
     ועוד
    -1.20
    tür
    -1.17
    Kaynak
    -1.17
     kapas
    -1.16
    POSITIVE LOGITS
    else
    1.68
    UT
    1.27
    th
    1.25
    t
    1.20
     otherwise
    1.20
    AT
    1.20
    av
    1.20
    in
    1.19
    C
    1.17
    ac
    1.16
    Activations Density 0.003%

    No Known Activations