© 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. 33394
    Prev
    Next
    INDEX
    Explanations

    video recording and configuration

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

    This neuron fires on programming‐style tokens—class/method names, code keywords, numeric literals, and other code artifacts.

    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
    ってみました
    -1.30
     its
    -1.23
    🗑
    -1.22
     personalización
    -1.17
     we
    -1.14
     they
    -1.13
    💷
    -1.13
    ῾
    -1.12
    天气
    -1.11
    יצד
    -1.11
    POSITIVE LOGITS
    espé
    1.20
     Hinsicht
    1.14
     still
    1.12
    Literat
    1.12
     trotzdem
    1.10
     demnach
    1.08
    große
    1.06
    ご購入
    1.05
    んだから
    1.04
     mea
    1.02
    Activations Density 0.001%

    No Known Activations