© 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. 34-GEMMASCOPE-RES-131K
    7. 3543
    Prev
    Next
    INDEX
    Explanations

    Oxford pronunciation and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    etti
    -0.76
     Creole
    -0.75
     線
    -0.74
    策
    -0.72
    절
    -0.70
     dicen
    -0.67
     entities
    -0.66
    agna
    -0.66
     藤
    -0.65
     gutt
    -0.65
    POSITIVE LOGITS
    sense
    1.20
     senses
    1.20
     Sense
    1.09
    Sense
    1.08
     sense
    1.03
    驶
    0.92
     yaşam
    0.88
     autoridades
    0.79
    defense
    0.78
     Sébastien
    0.78
    Activations Density 0.014%

    No Known Activations