© 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
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149474
    Prev
    Next
    INDEX
    Explanations

    new things and people

    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_29_width_262k_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
     socalled
    0.91
     wellknown
    0.90
     oftent
    0.83
    ({...
    0.82
    nestjs
    0.79
    <\
    0.78
    اته
    0.77
     фонбет
    0.76
    تعليم
    0.75
    reasonable
    0.75
    POSITIVE LOGITS
      
    1.47
       
    1.07
    </sup>
    0.95
        
    0.88
     новых
    0.85
    </sub>
    0.85
     নতুন
    0.80
     new
    0.80
     podcast
    0.80
    ऱ्यांना
    0.80
    Activations Density 0.001%

    No Known Activations