© 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. 20285
    Prev
    Next
    INDEX
    Explanations

    ex vivo studies

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

    Latin scientific phrases like "ex vivo" and abbreviations like "TLDR" or "tl;dr".

    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
     
    -2.61
     the
    -2.47
     to
    -2.22
     it
    -2.19
    C
    -2.17
     and
    -2.06
    -
    -1.97
    ers
    -1.94
     Such
    -1.89
     związane
    -1.88
    POSITIVE LOGITS
    ة
    2.48
    genheiten
    2.28
    ramientas
    2.09
    izielle
    2.08
    ⦆
    2.03
    ursales
    1.99
    uarine
    1.98
    ματα
    1.97
    irected
    1.94
    uride
    1.92
    Activations Density 0.020%

    No Known Activations