© 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. 66179
    Prev
    Next
    INDEX
    Explanations

    shin names and compounds

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

    Japanese names and words beginning with "Shin".

    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
    <td>
    -2.77
     icône
    -2.58
     abſ
    -2.56
     you
    -2.52
    </h3>
    -2.50
    焄
    -2.47
    秝
    -2.36
     Añade
    -2.27
    owulf
    -2.27
     Also
    -2.23
    POSITIVE LOGITS
    </b>
    3.03
    縠
    2.77
    {
    2.72
    و
    2.59
     mágica
    2.44
    \
    2.41
    All
    2.39
     thee
    2.30
     '
    2.28
    ねー
    2.19
    Activations Density 0.003%

    No Known Activations