© 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. 65229
    Prev
    Next
    INDEX
    Explanations

    centrifugation methods

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

    scientific techniques related to centrifugation in laboratory procedures.

    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
     they
    -1.35
    ácie
    -1.18
    They
    -1.14
     compagnia
    -1.13
     their
    -1.13
     you
    -1.12
    gnąć
    -1.10
    According
    -1.09
     meinte
    -1.08
    parently
    -1.07
    POSITIVE LOGITS
     centrifugation
    1.09
    örder
    1.06
    ítás
    0.94
     océ
    0.93
     rapide
    0.93
    Răsp
    0.91
    !
    0.91
     relev
    0.91
     halt
    0.90
    子弹
    0.90
    Activations Density 0.003%

    No Known Activations