© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40725
    Prev
    Next
    INDEX
    Explanations

    similarly followed by descriptor

    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
     in
    -2.72
     of
    -2.55
    </h4>
    -2.23
     for
    -2.19
     From
    -2.08
     Thanks
    -2.00
     The
    -1.95
    </strong>
    -1.95
     on
    -1.91
    ໊
    -1.85
    POSITIVE LOGITS
    卨
    2.17
    
    2.06
     新款
    2.03
    sandália
    1.94
     adatt
    1.94
     снова
    1.91
     ventured
    1.90
     Seeder
    1.82
    enerys
    1.77
    [
    1.77
    Activations Density 0.011%

    No Known Activations