© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68304
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code punctuation

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

    This neuron is primarily detecting literal constants (numeric or string literals) 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
     princí
    -1.12
     najlep
    -1.10
     spô
    -1.09
    Personally
    -1.02
     svoju
    -1.02
    sejarah
    -1.01
     informací
    -1.01
     vaš
    -1.00
     oeufs
    -1.00
     obrazov
    -0.99
    POSITIVE LOGITS
     other
    1.12
     этим
    1.00
    ";
    0.98
     ?>>
    0.97
    ();
    0.96
     Determines
    0.95
    setVerticalGroup
    0.93
     isso
    0.93
     after
    0.92
    __);
    0.92
    Activations Density 0.002%

    No Known Activations