© 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. 66067
    Prev
    Next
    INDEX
    Explanations

    brussel sprouts

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

    words related to technical or scientific terms, particularly in mathematical equations, biological names, and scholarly text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     decoracion
    -1.10
     surabaya
    -1.05
     vaisselle
    -1.04
     mueble
    -1.01
     bandung
    -1.00
     Gewer
    -0.99
     extranjero
    -0.98
     specialises
    -0.97
     giorgio
    -0.96
     conductas
    -0.96
    POSITIVE LOGITS
    itás
    1.16
    Élet
    1.06
    borderSide
    1.01
    artista
    0.98
    formik
    0.97
    ϝ
    0.93
     Игра
    0.93
    unitOfWork
    0.91
     ulica
    0.91
     VizieR
    0.90
    Activations Density 0.102%

    No Known Activations