© 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. 61501
    Prev
    Next
    INDEX
    Explanations

    android recyclerview

    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
     både
    -1.61
     <",
    -1.57
    </h1>
    -1.47
     WAY
    -1.45
    Ꮞ
    -1.42
    ต่
    -1.41
     maar
    -1.37
     pü
    -1.37
     autumn
    -1.36
    痛苦
    -1.36
    POSITIVE LOGITS
     your
    1.89
     verdieping
    1.54
    新潟
    1.53
    釭
    1.49
    着一
    1.45
    補足
    1.45
     всички
    1.45
    <bos>
    1.43
     asegur
    1.39
     cobran
    1.39
    Activations Density 0.004%

    No Known Activations