© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15112
    Prev
    Next
    INDEX
    Explanations

    api and uml schema

    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
    巿
    -2.05
     tertinggi
    -2.00
     helps
    -1.98
    可以说
    -1.96
     определяется
    -1.95
     एक
    -1.94
     disconcer
    -1.87
     starts
    -1.86
    های
    -1.84
     помогает
    -1.84
    POSITIVE LOGITS
    哢
    2.20
    uml
    2.19
    彀
    2.05
     cocin
    1.96
     Mischung
    1.91
     haupts
    1.87
     “
    1.83
    唻
    1.82
     spearheaded
    1.79
    牺
    1.79
    Activations Density 0.001%

    No Known Activations