© 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. 105995
    Prev
    Next
    INDEX
    Explanations

    class/component definitions after 'extends'

    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
    </h2>
    -1.73
     после
    -1.72
    仿佛
    -1.46
     discern
    -1.45
     Einige
    -1.43
    足以
    -1.39
    并且
    -1.38
     jarring
    -1.35
     inconce
    -1.33
     Their
    -1.32
    POSITIVE LOGITS
     is
    1.66
     carteles
    1.55
    borderSide
    1.54
    WebElementEntity
    1.52
     permesso
    1.52
     always
    1.51
    aş
    1.47
    "}}>
    1.46
     мужа
    1.45
     carcasa
    1.40
    Activations Density 0.036%

    No Known Activations