© 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. 34-GEMMASCOPE-RES-131K
    4. 103052
    Prev
    Next
    INDEX
    Explanations

    primary health care utilisation

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

    code-related elements like XML tags, compiler directives, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects XML/HTML markup, specifically element tags and their attributes enclosed in angle brackets.

    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
    Creating
    -0.95
     creates
    -0.95
     strives
    -0.92
     two
    -0.90
     Creating
    -0.89
     over
    -0.86
     sooooo
    -0.85
     HUGE
    -0.85
     burgeoning
    -0.84
     became
    -0.83
    POSITIVE LOGITS
    ources
    0.96
    lization
    0.93
     dando
    0.92
    atization
    0.90
    cles
    0.90
     بناء
    0.88
    ilization
    0.88
     серии
    0.88
    орга
    0.85
     andare
    0.84
    Activations Density 0.003%

    No Known Activations