Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12058
    Prev
    Next
    INDEX
    Explanations

    html elements and structure

    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_22/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
    UBLIC
    -1.27
    IKit
    -1.19
     the
    -1.16
    游戏中
    -1.15
     it
    -1.15
     of
    -1.14
     红色
    -1.14
    rafa
    -1.13
    different
    -1.12
     报告
    -1.10
    POSITIVE LOGITS
     pubblicato
    1.05
    やっと
    1.05
    твори
    1.02
    乃至
    1.01
     facilitating
    0.99
    7
    0.97
           
    0.97
    日目
    0.94
    2
    0.94
     bolster
    0.94
    Activations Density 0.001%

    No Known Activations