© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8460
    Prev
    Next
    INDEX
    Explanations

    whose, 의, యొక్క

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

    The neuron fires strongly on proper nouns and named entities (e.g. personal names, team names, places, organizations).

    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_31_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
     '
    0.70
    <0xE2>
    0.68
    _
    0.68
    "
    0.66
    начально
    0.66
    }
    0.65
    шел
    0.64
    “
    0.64
    1
    0.64
      
    0.61
    POSITIVE LOGITS
     యొక్క
    2.31
    ’
    2.30
    ның
    1.97
    자의
    1.96
    들의
    1.95
    사의
    1.93
    യുടെ
    1.89
    의
    1.88
    '
    1.88
    기의
    1.87
    Activations Density 2.408%

    No Known Activations