© 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. 3612
    Prev
    Next
    INDEX
    Explanations

    fluid followed by streams, percussion, beds, control

    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
    muñeca
    -0.96
     siendo
    -0.94
     algunos
    -0.92
    Chloroform
    -0.87
    ↵
    -0.84
    hdashline
    -0.84
    сунок
    -0.82
     совсем
    -0.82
    的一些
    -0.82
     algunas
    -0.81
    POSITIVE LOGITS
    ics
    1.20
    fluid
    1.14
     fluid
    1.06
    ized
    1.05
    い
    1.02
    ic
    1.00
    Fluid
    0.98
    น่า
    0.93
     Fluid
    0.92
     Mapper
    0.90
    Activations Density 0.019%

    No Known Activations