© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14220
    Prev
    Next
    INDEX
    Explanations

    levels, knowledge, type, because, patients, use, Kingdom, assess

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

    scientific medical content, particularly focusing on research findings, patient studies, and clinical observations.

    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
    更に
    -1.94
     dimana
    -1.27
    हरु
    -1.24
    の為
    -1.23
     skall
    -1.20
     می‌باشد
    -1.17
    事で
    -1.12
     Whilst
    -1.11
     whilst
    -1.11
     anyways
    -1.09
    POSITIVE LOGITS
     mida
    1.27
    ைக்
    1.23
    United
    1.23
     United
    1.20
     pérdidas
    1.20
    燜
    1.18
     beziehungs
    1.17
     Internet
    1.14
     chng
    1.14
    ackerel
    1.13
    Activations Density 0.483%

    No Known Activations