© 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. 10-GEMMASCOPE-RES-131K
    7. 102873
    Prev
    Next
    INDEX
    Explanations

    involves plasma exchange

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

    phrases that describe actions being performed, particularly in passive constructions like "found in," "paved over," or "collectively, the."

    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
    ที่จะ
    -1.34
     will
    -1.28
    scriptsize
    -1.18
    бва
    -1.17
    érios
    -1.16
    IsInitialized
    -1.16
     only
    -1.16
     than
    -1.16
     we
    -1.16
     mascarilla
    -1.13
    POSITIVE LOGITS
     همچنین
    1.17
     również
    1.16
    ็
    1.14
     mariana
    1.13
     paulo
    1.13
     для
    1.09
     suscit
    1.09
    的角色
    1.09
     вр
    1.08
     mesmas
    1.08
    Activations Density 0.200%

    No Known Activations