© 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. 12244
    Prev
    Next
    INDEX
    Explanations

    names ending in ar, el, ul, or un

    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
     has
    -1.96
     but
    -1.92
    ......
    -1.88
    </h3>
    -1.73
     new
    -1.73
     tells
    -1.66
     helps
    -1.60
    </th>
    -1.60
     should
    -1.59
     gets
    -1.59
    POSITIVE LOGITS
     kader
    1.88
    ⎔
    1.73
     risa
    1.72
     charmant
    1.70
    ,
    1.66
     normale
    1.66
     moza
    1.65
    镡
    1.62
     nabi
    1.61
    噚
    1.61
    Activations Density 0.015%

    No Known Activations