© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    space probe, organs, circle, rate, beams, coverage

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

    scientific or technical terminology related to physical structures or anatomical features.

    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
    𓋼
    -1.40
    BURGH
    -1.38
    氤
    -1.37
     oír
    -1.33
    ทุก
    -1.29
    🤙
    -1.29
     titulado
    -1.26
     positivas
    -1.26
    ב
    -1.24
    Después
    -1.23
    POSITIVE LOGITS
     such
    1.55
     molta
    1.40
    ほとん
    1.37
     отвечает
    1.31
     I
    1.30
     получает
    1.25
    すっ
    1.23
    凄く
    1.22
    いくつか
    1.20
    こういった
    1.19
    Activations Density 0.709%

    No Known Activations