© 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. 65520
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    technical or scientific terms and concepts, particularly in academic or medical contexts.

    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
     fully
    -0.87
    measurements
    -0.85
     or
    -0.84
     ดำ
    -0.84
     requer
    -0.83
    imeter
    -0.82
    ="{{
    -0.81
    ɴ
    -0.81
     ・
    -0.81
    //{
    -0.81
    POSITIVE LOGITS
     Zusammensetzung
    1.05
    Lors
    0.95
    吋
    0.90
    已经在
    0.86
     risposte
    0.86
    擅长
    0.85
    معرفی
    0.85
    量
    0.85
    當初
    0.85
    ⍝
    0.85
    Activations Density 0.076%

    No Known Activations