© 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. 48275
    Prev
    Next
    INDEX
    Explanations

    place names and identification

    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
     camiset
    -2.17
    彣
    -1.95
    妘
    -1.92
     放題
    -1.88
     técn
    -1.86
    䨻
    -1.84
    旆
    -1.81
    〼
    -1.75
     école
    -1.71
    튿
    -1.70
    POSITIVE LOGITS
    ↵
    2.27
     i
    1.91
    </strong>
    1.86
    \
    1.80
     is
    1.78
    ↵↵↵
    1.74
     l
    1.74
     you
    1.73
     they
    1.65
    ↵↵↵↵↵↵↵↵↵↵↵
    1.63
    Activations Density 0.005%

    No Known Activations