© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99745
    Prev
    Next
    INDEX
    Explanations

    macro or micro

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

    scientific prefixes like "macro-", "macroscopic", or "macrophage" in medical and scientific text.

    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
    鹮
    -2.55
     mohou
    -2.22
    鹩
    -2.19
    ながらも
    -2.11
    砹
    -2.06
    这事
    -2.02
    рії
    -2.00
    悫
    -1.98
    leanor
    -1.98
    赑
    -1.98
    POSITIVE LOGITS
    In
    2.81
    f
    2.64
    as
    2.48
    0
    2.39
    d
    2.33
    3
    2.33
    r
    2.31
    IN
    2.27
    er
    2.23
     &
    2.23
    Activations Density 0.017%

    No Known Activations