© 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. 34-GEMMASCOPE-RES-131K
    7. 99723
    Prev
    Next
    INDEX
    Explanations

    code template snippets

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

    This neuron detects templating‐language interpolation markers (e.g. “{{”, “{$”, “<%=” and related template 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_34/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
    このように
    -0.81
     grotes
    -0.78
    など
    -0.77
     spurt
    -0.77
     bête
    -0.75
    および
    -0.75
    BirthDate
    -0.74
    Detected
    -0.74
    個人的には
    -0.73
     bibliographies
    -0.73
    POSITIVE LOGITS
     prefix
    1.00
     there
    1.00
    prefix
    0.98
    ,{\
    0.91
     our
    0.89
     ведом
    0.88
     naszego
    0.87
     name
    0.87
    Prefix
    0.85
    RSpec
    0.85
    Activations Density 0.025%

    No Known Activations