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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-1b-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
    価
    0.78
    ৃত্ত
    0.75
     way
    0.72
     hijacked
    0.71
    猾
    0.71
     supersonic
    0.71
     manner
    0.70
    wne
    0.69
     warriors
    0.68
    immunoassay
    0.68
    POSITIVE LOGITS
     administração
    0.75
    vest
    0.74
     बेल
    0.74
     effetti
    0.72
    పై
    0.69
    ogen
    0.67
    Charge
    0.67
    菏
    0.67
     ది
    0.67
    ove
    0.66
    Activations Density 0.203%

    No Known Activations