© 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. 130876
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    ↵↵
    -1.88
    </h4>
    -1.66
     on
    -1.61
     solchen
    -1.42
     donde
    -1.35
     autre
    -1.33
    を設置
    -1.32
    を用意
    -1.31
     astonishing
    -1.25
     elle
    -1.23
    POSITIVE LOGITS
     how
    1.85
     whether
    1.66
    </i>
    1.57
    “
    1.48
     they
    1.48
     demonstrates
    1.44
     why
    1.41
    .」
    1.40
     Wikiseite
    1.39
     cerdas
    1.39
    Activations Density 0.024%

    No Known Activations