© 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. 34-GEMMASCOPE-RES-131K
    7. 65072
    Prev
    Next
    INDEX
    Explanations

    exo, ecto, endo prefixes

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

    prefixes related to scientific terminology, particularly "exo-" and similar prefixes in biological and chemical terms.

    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_34/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
    钧
    -0.71
    urea
    -0.71
    unj
    -0.71
     цент
    -0.69
    garh
    -0.68
    ЩЕ
    -0.68
    ppl
    -0.68
    adores
    -0.66
     Indie
    -0.65
    цтва
    -0.65
    POSITIVE LOGITS
     endo
    0.90
     Exo
    0.84
     exo
    0.83
    íst
    0.81
     horseback
    0.75
    umented
    0.71
    RotationOrder
    0.70
     whereas
    0.70
     Konzer
    0.70
    涩
    0.69
    Activations Density 0.074%

    No Known Activations