© 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. 59625
    Prev
    Next
    INDEX
    Explanations

    Liam names and Crohn's disease

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

    names of people, especially surnames like Payne, Liam, and CPA abbreviations.

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

    This neuron activates on capitalized named-entity tokens, especially personal and other proper names.

    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
    );
    -2.69
     owing
    -2.44
    ில்
    -2.42
    瞜
    -2.41
    笵
    -2.36
    !”
    -2.30
     attentive
    -2.27
     championed
    -2.25
    bumptech
    -2.23
    訁
    -2.20
    POSITIVE LOGITS
    $
    3.30
    場所に
    2.41
     him
    2.16
    跻
    2.11
    '."
    2.09
    ✴
    2.09
     righ
    2.03
    —.
    1.96
    %
    1.95
     regal
    1.93
    Activations Density 0.004%

    No Known Activations