© 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. 21966
    Prev
    Next
    INDEX
    Explanations

    area grassland extracellular

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

    measurements of land area in hectares.

    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
    ocarditis
    -2.52
    ୩
    -2.50
    ຝ
    -2.50
    鳧
    -2.36
    isieren
    -2.36
    鈇
    -2.31
    راسیون
    -2.30
    瑧
    -2.28
    檬
    -2.28
     Dirección
    -2.28
    POSITIVE LOGITS
     \
    3.88
    <em>
    2.75
    <bos>
    2.55
     usual
    2.52
    <td>
    2.45
    is
    2.44
     Focusing
    2.39
     ''
    2.38
    at
    2.36
    actéristi
    2.30
    Activations Density 0.005%

    No Known Activations