© 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. 102228
    Prev
    Next
    INDEX
    Explanations

    various types of

    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
     spac
    -1.64
    ？
    -1.63
     trois
    -1.56
     where
    -1.47
    ciles
    -1.44
    风险
    -1.42
    "
    -1.40
    roke
    -1.38
    covers
    -1.38
    кономи
    -1.37
    POSITIVE LOGITS
    各样的
    1.98
    ashqai
    1.63
     different
    1.63
     various
    1.63
    </em>
    1.62
     jednotliv
    1.55
     aspects
    1.53
     types
    1.53
    AutoresizingMask
    1.48
     مختلف
    1.47
    Activations Density 0.074%

    No Known Activations