© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130669
    Prev
    Next
    INDEX
    Explanations

    cerebrospinal fluid, spinal fluid

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

    technical terminology in programming and scientific documents.

    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_10/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
     also
    -1.76
     more
    -1.48
     They
    -1.41
    うーん
    -1.41
     of
    -1.41
     =
    -1.38
     who
    -1.38
     diário
    -1.36
     few
    -1.34
     very
    -1.30
    POSITIVE LOGITS
     ligera
    1.48
    怎么回事
    1.43
    }</
    1.42
     acoged
    1.41
     aislada
    1.38
    IActionResult
    1.38
     schrij
    1.37
     is
    1.35
     atractiva
    1.33
     gruesa
    1.33
    Activations Density 0.177%

    No Known Activations