© 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. 111065
    Prev
    Next
    INDEX
    Explanations

    trampoline park, pool

    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
     burbu
    -1.89
    皷
    -1.76
    鏐
    -1.74
    謌
    -1.73
     发型
    -1.71
     grij
    -1.70
    琲
    -1.66
    ]^
    -1.63
    Cevap
    -1.63
    豸
    -1.60
    POSITIVE LOGITS
    0
    1.77
    ↵↵
    1.66
     *
    1.49
     '
    1.49
    R
    1.48
     that
    1.38
    だが
    1.37
     bauen
    1.34
    //
    1.32
    <em>
    1.30
    Activations Density 0.016%

    No Known Activations