© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3562
    Prev
    Next
    INDEX
    Explanations

    enantiomeric purity

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

    scientific and technical language related to high purity or separation processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    antwoorde
    -0.71
    ália
    -0.66
    ysuckle
    -0.66
    骶
    -0.65
     عام
    -0.65
    lipp
    -0.64
    UGHTER
    -0.63
    vation
    -0.63
    ﾞ
    -0.63
    HUB
    -0.62
    POSITIVE LOGITS
     purity
    6.25
     pure
    5.00
     Purity
    4.63
    pure
    4.41
    Purity
    4.34
     purer
    4.25
    Pure
    4.19
     pureza
    4.09
     purest
    4.06
     Pure
    4.03
    Activations Density 0.119%

    No Known Activations