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. 7602
    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
    Ɖ
    0.87
     introspection
    0.84
     autobi
    0.83
    甛
    0.82
     ఎన్నిక
    0.81
     comprobar
    0.81
     uphe
    0.80
     reformulation
    0.80
     cáncer
    0.79
    Ж
    0.79
    POSITIVE LOGITS
    _
    0.80
     freaking
    0.79
    деа
    0.75
    и
    0.71
    '.
    0.67
    )。
    0.67
     yelling
    0.65
    and
    0.64
    akha
    0.63
    imetro
    0.63
    Activations Density 0.000%

    No Known Activations