© 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. 119551
    Prev
    Next
    INDEX
    Explanations

    porphy, prawn, ferrous, generative

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

    words related to food items, professional titles, and technical 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_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
    媜
    -2.61
    鰱
    -2.42
     scrutin
    -2.39
    鐿
    -2.38
    Ꭳ
    -2.36
    𓆜
    -2.34
    囌
    -2.34
    鼉
    -2.30
    随即
    -2.30
     Increases
    -2.30
    POSITIVE LOGITS
     of
    2.48
    >
    2.39
     they
    2.30
    猻
    2.30
    L
    2.28
     \
    2.27
     сотрудников
    2.27
    ↵↵
    2.25
    ꒥
    2.23
    mathrm
    2.19
    Activations Density 0.006%

    No Known Activations