© 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. 61414
    Prev
    Next
    INDEX
    Explanations

    airline industry topics

    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
    '
    -2.72
    </em>
    -2.66
    的就
    -2.53
     o
    -2.52
     However
    -2.50
    </h4>
    -2.48
    他就
    -2.45
    ’
    -2.45
    </sup>
    -2.41
     She
    -2.41
    POSITIVE LOGITS
    Ꮂ
    2.81
    㩒
    2.63
    ܜ
    2.61
    鳚
    2.61
    ⁉
    2.58
     pérd
    2.56
    臏
    2.55
    劄
    2.48
    狆
    2.48
    ｕ
    2.47
    Activations Density 0.003%

    No Known Activations