© 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. 40300
    Prev
    Next
    INDEX
    Explanations

    Nagasaki Bio, Mahatma Gandhi

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

    technical terms, abbreviations and specialized vocabulary in scientific or technical documents.

    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
    ⩖
    -2.83
    </em>
    -2.73
    糨
    -2.69
    ྄
    -2.66
    噲
    -2.61
    齶
    -2.56
    苤
    -2.53
    ⩕
    -2.48
    でしたが
    -2.45
    
    -2.38
    POSITIVE LOGITS
     این
    2.61
    เกง
    2.41
    Schule
    2.30
    ⇰
    2.25
    byId
    2.25
     —
    2.25
    沺
    2.23
     –
    2.20
    ൅
    2.20
    周泽
    2.16
    Activations Density 0.047%

    No Known Activations