© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    contribute to

    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
    ꜆
    -3.00
    其他
    -2.91
    秾
    -2.70
    -2.66
    y
    -2.63
    ي
    -2.63
    最大
    -2.58
    ꔹ
    -2.53
    }$
    -2.53
    
    -2.50
    POSITIVE LOGITS
    </h4>
    3.48
    </em>
    3.48
    ↵
    2.73
    攆
    2.56
    椟
    2.50
    摃
    2.45
    他还
    2.42
     migh
    2.42
    “
    2.39
     We
    2.36
    Activations Density 0.015%

    No Known Activations