© 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. 73948
    Prev
    Next
    INDEX
    Explanations

    HTML titles, code delimiters, questions

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

    The neuron detects Javadoc‐generated HTML header metadata (e.g. the “<!-- Generated by javadoc … -->” comments and associated <title> lines).

    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
     Tenggara
    -1.13
     who
    -1.01
    слен
    -0.99
     kaip
    -0.98
    activation
    -0.98
     Tuhan
    -0.96
     culte
    -0.95
    éos
    -0.92
     кто
    -0.90
    сква
    -0.90
    POSITIVE LOGITS
     также
    1.19
     amenaz
    1.11
     również
    1.10
     mandatario
    1.10
     paroisse
    1.00
    であ
    1.00
    soldiers
    0.96
    Hilsen
    0.96
     gestalten
    0.95
     관련
    0.94
    Activations Density 0.000%

    No Known Activations