© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111342
    Prev
    Next
    INDEX
    Explanations

    code keywords

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

    the keyword "else" in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly responds to the opening brace “{” that follows an “else” keyword, i.e. it detects else‐blocks 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_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
     infatti
    -1.59
     nõ
    -1.49
    ingresso
    -1.40
    你和
    -1.39
     gyvento
    -1.37
     dúvida
    -1.37
    uomo
    -1.36
    鼷
    -1.35
     azonban
    -1.33
    nappropriate
    -1.32
    POSITIVE LOGITS
     "
    1.69
     ”
    1.58
     „
    1.52
     other
    1.40
     '
    1.39
     “
    1.34
    }_{\
    1.33
    ”,
    1.30
    .
    1.27
    注釈
    1.27
    Activations Density 0.002%

    No Known Activations