© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9139
    Prev
    Next
    INDEX
    Explanations

    site/ or site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     damning
    1.00
    തല
    0.98
     accountable
    0.97
    ედა
    0.95
    ر
    0.95
     Ratt
    0.94
    modeling
    0.93
    
    0.93
    깊
    0.92
    ရေ
    0.92
    POSITIVE LOGITS
     cuyo
    1.07
     जिसमें
    1.06
    iswa
    1.05
     जिसे
    1.05
    вый
    1.02
     ابتدا
    1.01
     leave
    1.01
    जिसे
    1.00
     mist
    0.99
     obstruct
    0.98
    Activations Density 0.003%

    No Known Activations