© 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. 42259
    Prev
    Next
    INDEX
    Explanations

    javascript function syntax

    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
     \
    -1.49
     The
    -1.40
    雷霆
    -1.34
    次に
    -1.33
     no
    -1.30
     they
    -1.30
     transcendent
    -1.29
    がみ
    -1.28
    ollectionView
    -1.27
     Momente
    -1.27
    POSITIVE LOGITS
    </h2>
    2.16
    </h4>
    1.64
    </b>
    1.62
    WWE
    1.48
    /");
    1.43
    isit
    1.37
    inigung
    1.34
    ynarod
    1.34
    itv
    1.33
    และ
    1.32
    Activations Density 0.004%

    No Known Activations