© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123808
    Prev
    Next
    INDEX
    Explanations

    chemical names with numbers

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

    chemical compound notations with numbers, particularly those ending in O3.

    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
     There
    -2.48
     Чтобы
    -2.44
     After
    -2.30
     selben
    -2.30
     Because
    -2.27
    PreExecute
    -2.25
     olvid
    -2.20
     luchar
    -2.19
    這些
    -2.17
     recomendar
    -2.17
    POSITIVE LOGITS
    ↵
    3.30
     ウィメンズ
    2.73
     of
    2.52
    葙
    2.48
    渼
    2.45
    ꜆
    2.39
     tetapi
    2.38
    n
    2.23
    5
    2.19
    ↵↵↵↵
    2.16
    Activations Density 0.032%

    No Known Activations