© 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. 99178
    Prev
    Next
    INDEX
    Explanations

    `King`, `syringae`, `aspartic`, `Hindu`

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

    scientific and technical terms, particularly chemical compounds, biological entities, and specialized technology terms.

    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
    䉴
    -1.99
    imanapun
    -1.91
     incrível
    -1.70
    DESCRIPCIÓN
    -1.70
     comienzos
    -1.68
    ve
    -1.66
     encontrados
    -1.64
    仍然
    -1.63
     búsquedas
    -1.63
     potenciales
    -1.62
    POSITIVE LOGITS
    '
    1.74
    ammlung
    1.70
     Toilette
    1.68
    போ
    1.55
    *
    1.55
    ranslated
    1.53
     harten
    1.53
    Suppose
    1.53
     नए
    1.52
    trucks
    1.51
    Activations Density 0.056%

    No Known Activations