© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64522
    Prev
    Next
    INDEX
    Explanations

    entity or Creature followed by Set or period

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

    This neuron activates on code identifiers and imports referring to “entity” (e.g. Entity, net.minecraft.entity, getCreature).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵
    -1.09
    细腻
    -1.09
     jueves
    -1.09
     system
    -1.04
     Eingang
    -1.02
     miércoles
    -0.96
     estreno
    -0.95
     réglable
    -0.95
    陝
    -0.94
     espectáculo
    -0.92
    POSITIVE LOGITS
    amaño
    1.20
     she
    1.20
    ピール
    1.13
    trout
    1.12
     attente
    1.11
    に行ってきました
    1.09
    творення
    1.09
    ветить
    1.09
    InputChange
    1.05
    zzling
    1.03
    Activations Density 0.000%

    No Known Activations