© 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. 124144
    Prev
    Next
    INDEX
    Explanations

    species, nov

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

    scientific notation for newly described species, particularly the abbreviation "sp. nov." or "n. sp." in taxonomic literature.

    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
     cantora
    -1.34
     voleva
    -1.34
    ния
    -1.30
    резать
    -1.27
    ोर्ट
    -1.24
     bayern
    -1.22
    рецепт
    -1.21
    躂
    -1.20
    封闭
    -1.20
    𝙧
    -1.18
    POSITIVE LOGITS
    —
    1.36
     '
    1.20
     Motions
    1.15
    айт
    1.14
     pady
    1.13
     寿
    1.12
    的呢
    1.11
    tráfico
    1.11
    1
    1.10
    그
    1.10
    Activations Density 0.044%

    No Known Activations