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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7605
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-4b-it/resid_post
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     álbum
    1.68
    ქმედ
    1.61
    वरिश
    1.57
    ፍተኛ
    1.57
    ်
    1.56
     né
    1.50
     deserial
    1.48
     bunun
    1.47
     thé
    1.46
     genero
    1.44
    POSITIVE LOGITS
    ل
    2.18
    ১
    1.88
    क्रिय
    1.82
    ר
    1.81
    方式
    1.78
    ्स
    1.78
    s
    1.77
    ಯಲ್ಲಿ
    1.76
    個セット
    1.71
    hopping
    1.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.