© 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. 15671
    Prev
    Next
    INDEX
    Explanations

    affiliation correction

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

    The neuron fires on the section heading or label “affiliation” in academic/article metadata.

    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
     will
    -1.07
     begin
    -1.02
    工作室
    -1.01
     глазах
    -0.98
     Schweiz
    -0.97
    它的
    -0.97
    ɓ
    -0.95
    érc
    -0.94
    工程
    -0.93
    ✨:
    -0.92
    POSITIVE LOGITS
     Fähig
    1.21
     cúp
    1.16
     inspección
    1.10
    selben
    1.08
     ACCIDENT
    1.06
    espero
    1.06
     armazenamento
    1.05
     possibilidades
    1.04
    Vezi
    1.02
     máscaras
    1.02
    Activations Density 0.000%

    No Known Activations