© 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. 34-GEMMASCOPE-RES-131K
    7. 55612
    Prev
    Next
    INDEX
    Explanations

    names starting with bha

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

    The neuron fires on occurrences of the “Bharat”/“Bharti” root in named entities (e.g. Bharat Masrani, Bharat Gas, Bharti Airtel, Bharatiya).

    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
    cris
    -0.75
     větší
    -0.74
     samodziel
    -0.73
     Harman
    -0.73
    シルバー
    -0.72
    وسط
    -0.70
    ارتمان
    -0.70
     fearless
    -0.69
    //
    -0.69
     ベビー
    -0.68
    POSITIVE LOGITS
    quinha
    0.71
     żel
    0.71
     Auxiliary
    0.71
    Auxiliary
    0.70
    apj
    0.69
    yun
    0.68
    ódz
    0.68
    aider
    0.67
    '));
    0.66
    ijt
    0.66
    Activations Density 0.023%

    No Known Activations