© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71732
    Prev
    Next
    INDEX
    Explanations

    Valletta, transceiver, epithelium, Orientalism, Rutherford, NMEA, Lives Matter, Kombat, urticaria, Khru Bah

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

    place names and geographic locations.

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

    The main thing this neuron does is detect proper-name tokens (capitalized named entities).

    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
    8
    -3.34
    3
    -3.23
    7
    -3.17
    9
    -3.11
    6
    -3.11
    4
    -3.05
    1
    -3.02
    s
    -2.91
    5
    -2.75
    An
    -2.67
    POSITIVE LOGITS
      
    2.72
    GHI
    2.14
    殍
    2.09
     prennent
    2.06
    鹉
    2.00
    htb
    1.98
    自由に
    1.96
    合わせた
    1.94
    峤
    1.94
    はっきり
    1.93
    Activations Density 0.041%

    No Known Activations