© 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. 33148
    Prev
    Next
    INDEX
    Explanations

    medical and scientific suffixes and terms

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

    scientific prefixes and chemical/medical terminology, especially in fields like biochemistry, neurology, and pharmacology.

    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
    m
    -3.31
    when
    -2.70
    b
    -2.64
    T
    -2.61
    of
    -2.59
    S
    -2.58
     bogor
    -2.42
     veränder
    -2.38
    lossians
    -2.33
    de
    -2.30
    POSITIVE LOGITS
    𓐍
    2.69
     قبل
    2.33
    𖣘
    2.31
     Avrupa
    2.27
    ꔹ
    2.23
     ilustra
    2.20
    𖣔
    2.20
     reseña
    2.19
     profesora
    2.17
    Ꮼ
    2.17
    Activations Density 0.484%

    No Known Activations