© 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. 68792
    Prev
    Next
    INDEX
    Explanations

    TxDOT and anaerobic

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

    characters or symbols in non-English writing systems, especially Chinese/Japanese characters and numbered lists.

    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
    n
    -2.64
    '
    -2.48
    h
    -2.41
    k
    -2.39
    r
    -2.36
    c
    -2.30
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.23
    z
    -2.23
    é
    -2.17
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.16
    POSITIVE LOGITS
    foglio
    2.38
     such
    2.16
    tvguide
    2.16
    珢
    2.16
     farben
    2.14
    asının
    2.13
     Melhor
    2.11
    𝄆
    2.09
     Ensino
    2.09
    ichtete
    2.09
    Activations Density 0.001%

    No Known Activations