© 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. 22-GEMMASCOPE-RES-131K
    7. 33653
    Prev
    Next
    INDEX
    Explanations

    brand names and web links

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

    The neuron activates on sequences of uppercase tokens that form people’s names (especially surnames) in bylines or headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.38
     The
    -1.29
     a
    -1.26
     an
    -1.23
    あー
    -1.13
    A
    -1.13
     Create
    -1.09
     Therefore
    -1.09
    As
    -1.07
    ほら
    -1.05
    POSITIVE LOGITS
    がありますが
    1.59
    もあって
    1.56
    があるので
    1.46
    もあります
    1.46
    もありますが
    1.41
    でしょうね
    1.40
    もあるので
    1.38
    erobic
    1.35
    と思っている
    1.35
    があります
    1.34
    Activations Density 0.004%

    No Known Activations