© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84069
    Prev
    Next
    INDEX
    Explanations

    templating language closing delimiters

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

    The neuron is responding to numeric literals (integer values) embedded in code or template markup.

    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
     to
    -1.46
     ži
    -1.19
    了一种
    -1.07
     mangá
    -1.03
    igung
    -1.02
     technik
    -0.98
     žal
    -0.98
    ACIONAL
    -0.97
     Ministério
    -0.97
     of
    -0.97
    POSITIVE LOGITS
    ↵
    1.45
     your
    1.41
    或者
    1.10
     PLWABN
    1.06
     εδώ
    1.04
    現在の
    1.03
     fiabilidad
    1.02
    书籍
    1.01
     immediatamente
    1.00
     durabilidad
    1.00
    Activations Density 0.010%

    No Known Activations