© 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. 71326
    Prev
    Next
    INDEX
    Explanations

    Java libraries and frameworks

    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
     That
    -2.59
     hinder
    -2.23
     Didn
    -2.19
    section
    -2.05
     vary
    -2.03
     relieve
    -2.03
     resemble
    -2.03
     dunklen
    -2.03
     Когда
    -2.00
    mbda
    -1.98
    POSITIVE LOGITS
    綃
    2.14
     レスト
    2.09
    霂
    2.08
    ri
    2.03
    
    1.98
    简约
    1.95
    咵
    1.95
     activit
    1.92
     foro
    1.91
     comis
    1.89
    Activations Density 0.001%

    No Known Activations