© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119913
    Prev
    Next
    INDEX
    Explanations

    legal citation parts

    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
     ὁ
    -1.59
     minera
    -1.59
     }],
    -1.54
     الشاشة
    -1.52
    ++,
    -1.52
    </i>
    -1.49
     يبدو
    -1.48
     Biologie
    -1.46
     creativos
    -1.46
    ฿
    -1.45
    POSITIVE LOGITS
    '
    2.11
    <bos>
    1.73
    mathrm
    1.57
    
    1.56
    -
    1.46
    to
    1.36
    tion
    1.35
    or
    1.32
     trochę
    1.31
     несколько
    1.29
    Activations Density 0.039%

    No Known Activations