© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5932
    Prev
    Next
    INDEX
    Explanations

    special character sequences

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

    The neuron detects mentions of institutions or organizational entities (e.g., clinic, hospital, staff, company, insurance).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marrón
    0.91
    ಿಕೊಂಡ
    0.90
    йся
    0.88
    ченные
    0.88
    ñoz
    0.86
    íns
    0.85
    𝘆
    0.85
    нів
    0.84
    𝙚
    0.84
    𝙮
    0.84
    POSITIVE LOGITS
    l
    0.78
     equivalently
    0.76
    d
    0.75
    lz
    0.71
     Occurrence
    0.69
     truthfully
    0.69
    leness
    0.68
    ोस
    0.66
     authored
    0.66
     besides
    0.65
    Activations Density 0.000%

    No Known Activations