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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 2
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    на
    0.41
    تين
    0.38
     ovog
    0.36
    ൈ
    0.35
     prefque
    0.32
    るので
    0.32
     pouquinho
    0.32
    ت
    0.32
    ן
    0.32
    ід
    0.32
    POSITIVE LOGITS
    and
    0.43
     the
    0.37
    )
    0.37
    ación
    0.35
    ana
    0.34
     an
    0.33
    ong
    0.33
    <0x0D>
    0.33
    ens
    0.32
     Empresas
    0.32
    Activations Density 4.800%

    No Known Activations