© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67752
    Prev
    Next
    INDEX
    Explanations

    Uttar Pradesh, Andhra Pradesh, atrial fibrillation

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

    references to Indian states, particularly "Andhra Pradesh" and "Uttar Pradesh".

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

    The neuron fires on mentions of Indian state names ending with “Pradesh,” e.g. “Uttar Pradesh” or “Andhra Pradesh.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    珰
    -2.91
    ↵
    -2.83
    
    -2.70
    ⢫
    -2.59
    ll
    -2.58
    쨩
    -2.53
    {
    -2.47
    罴
    -2.41
    鹩
    -2.38
    Ꮀ
    -2.34
    POSITIVE LOGITS
    AutoresizingMask
    2.59
    有
    2.53
     یا
    2.45
    躥
    2.45
     étab
    2.38
    Ꮟ
    2.34
    咐
    2.31
     rafra
    2.30
    使
    2.28
    或
    2.27
    Activations Density 0.006%

    No Known Activations