© 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. 129286
    Prev
    Next
    INDEX
    Explanations

    wide variety, medication effectiveness, muscle group

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

    technical terms in specialized domains like medicine, technology, and science.

    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
     折りたたみ
    -0.89
     kalori
    -0.87
     connais
    -0.86
     terapi
    -0.85
    Zitat
    -0.84
    Produzione
    -0.84
     donnés
    -0.83
    綺麗に
    -0.83
     réessayer
    -0.83
    ragende
    -0.82
    POSITIVE LOGITS
     regarding
    1.00
    izung
    0.93
     as
    0.89
     about
    0.86
     when
    0.86
     agencias
    0.82
    ("${
    0.81
     leitet
    0.79
    izon
    0.79
     K
    0.79
    Activations Density 0.133%

    No Known Activations