© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    fluoropolymer materials and non-stick surfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    _
    -2.80
    </i>
    -2.20
     the
    -2.06
     zahlreichen
    -2.03
     
    -2.00
    ?
    -1.98
    </td>
    -1.92
    -
    -1.84
    <b>
    -1.80
    IN
    -1.76
    POSITIVE LOGITS
    ه
    1.97
    ᯅ
    1.96
    粉色
    1.89
    滹
    1.88
    сшта
    1.80
    鳢
    1.78
    歃
    1.77
     Франция
    1.77
    هی
    1.73
     चीज़ों
    1.73
    Activations Density 0.007%

    No Known Activations