© 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. 10-GEMMASCOPE-RES-131K
    7. 68532
    Prev
    Next
    INDEX
    Explanations

    Amy, apple, earned, insider, ship

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

    This neuron detects mentions of named entities such as brand names, organizations, and other proper nouns.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     these
    -1.63
    these
    -1.48
    这两
    -1.41
    億円
    -1.35
    These
    -1.33
    Estos
    -1.30
     этом
    -1.26
     этих
    -1.25
     quelcon
    -1.24
    essero
    -1.23
    POSITIVE LOGITS
     agreed
    1.41
     additional
    1.41
    ele
    1.28
     beginning
    1.23
     offer
    1.23
     even
    1.20
    やってる
    1.19
     continued
    1.18
    formatics
    1.18
     beginnings
    1.16
    Activations Density 0.045%

    No Known Activations