© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69627
    Prev
    Next
    INDEX
    Explanations

    oxidase, ase, pathway

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

    abbreviations and acronyms in scientific and technical contexts.

    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
    蟶
    -2.13
     sprüche
    -1.97
     sâ
    -1.95
    ༵
    -1.91
    diese
    -1.84
     estadounid
    -1.84
    戆
    -1.84
     mâ
    -1.82
    地图
    -1.79
     strategia
    -1.77
    POSITIVE LOGITS
    1
    2.11
    ?
    2.06
    n
    1.91
    s
    1.77
    t
    1.76
    全都
    1.72
    3
    1.69
     ovviamente
    1.69
    7
    1.68
    !!!!!!
    1.66
    Activations Density 0.033%

    No Known Activations