© 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. 32571
    Prev
    Next
    INDEX
    Explanations

    free health and legal services

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

    official government and organizational entities or departments, particularly those related to health, safety, and public services.

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

    The neuron fires on mentions of an Australian pregnancy and lactation counselling service (e.g. “Australian pregnancy and lactation counselling”).

    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
    🫑
    -0.82
    اية
    -0.76
    viewController
    -0.74
    ape
    -0.72
    ഖ
    -0.69
    adilla
    -0.68
    ципа
    -0.68
    nés
    -0.68
    
    -0.68
    ★★★★☆
    -0.68
    POSITIVE LOGITS
     Ph
    0.98
     ph
    0.86
    Ph
    0.85
    🇷
    0.75
    acherous
    0.75
    Vent
    0.73
     morpho
    0.70
     FRE
    0.69
    ícil
    0.69
    胰
    0.67
    Activations Density 0.020%

    No Known Activations