© 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. 10-GEMMASCOPE-RES-131K
    7. 84890
    Prev
    Next
    INDEX
    Explanations

    code snippet examples

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

    The neuron fires on the word “snippet” (i.e. the marker introducing code snippets).

    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
    {
    -2.58
     cherish
    -2.36
    or
    -2.23
    ⃚
    -2.13
    }
    -2.09
     видит
    -2.03
    战胜
    -2.02
    歼
    -2.00
    ”;
    -1.99
     understand
    -1.98
    POSITIVE LOGITS
    赑
    2.81
     volando
    2.50
    section
    2.48
     imprescin
    2.45
    饪
    2.33
    是我的
    2.33
    臜
    2.33
    勦
    2.33
     possono
    2.33
     comien
    2.33
    Activations Density 0.003%

    No Known Activations