© 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. 38854
    Prev
    Next
    INDEX
    Explanations

    Wyatt, TMP, tinnitus, TCU, regenerative

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

    The neuron is a named-entity detector, activating on proper names, titles, and specialized terms.

    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
    {
    -3.53
    ↵
    -2.66
     beinahe
    -2.53
     Hoping
    -2.42
     Pushing
    -2.42
     avec
    -2.38
     Füßen
    -2.38
     praktisch
    -2.36
     Previously
    -2.34
     Achieving
    -2.33
    POSITIVE LOGITS
    荜
    3.27
    you
    3.06
     estudante
    2.89
     testimon
    2.86
    Ꮨ
    2.84
    檍
    2.81
    ндарт
    2.61
     prode
    2.52
     nostra
    2.48
    鞴
    2.47
    Activations Density 0.031%

    No Known Activations