© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44739
    Prev
    Next
    INDEX
    Explanations

    ginkgo biloba shop

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

    references to coffee shops in text.

    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
    m
    -2.58
    ”,
    -2.33
    ",
    -2.20
    те
    -2.20
    la
    -2.17
    ING
    -2.14
    x
    -2.06
    ли
    -2.05
    )"
    -2.05
    re
    -2.03
    POSITIVE LOGITS
    苼
    2.11
    取决
    2.11
    犼
    2.09
    曩
    2.05
    轂
    2.02
    亖
    1.98
    偁
    1.96
    神
    1.95
    鱔
    1.94
     استناد
    1.91
    Activations Density 0.021%

    No Known Activations