© 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. 10-GEMMASCOPE-RES-131K
    7. 72644
    Prev
    Next
    INDEX
    Explanations

    Gustavus, dimerization, Institut für

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

    words referring to a dimer or dimeric structure in scientific contexts.

    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
     were
    -2.67
     decidedly
    -2.66
    .,
    -2.61
     spectacular
    -2.56
    —-
    -2.53
     predominantly
    -2.50
     It
    -2.48
     suitably
    -2.48
     continually
    -2.48
     a
    -2.45
    POSITIVE LOGITS
    vantaged
    3.17
     primera
    2.63
    一会儿
    2.58
    蹋
    2.55
    馐
    2.45
    慥
    2.39
    utches
    2.28
    tellar
    2.27
    atég
    2.25
    ۉ
    2.25
    Activations Density 0.005%

    No Known Activations