© 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. 105801
    Prev
    Next
    INDEX
    Explanations

    from here/there

    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
    ↵↵
    -1.96
    ↵
    -1.71
     in
    -1.59
    も行
    -1.35
    鸸
    -1.34
     DELHI
    -1.32
    Étymologie
    -1.32
    นี
    -1.32
    lerini
    -1.31
     this
    -1.30
    POSITIVE LOGITS
    熥
    1.98
    ar
    1.91
    The
    1.88
    hline
    1.70
    晚上
    1.66
    ll
    1.61
    ،
    1.61
    ó
    1.59
    特に
    1.57
     Your
    1.55
    Activations Density 0.005%

    No Known Activations