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. 29-GEMMASCOPE-2-RES-65K
    4. 1269
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post
    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
     deference
    0.65
     desperation
    0.64
    かん
    0.64
     Sosa
    0.61
     oddly
    0.61
    vDash
    0.60
     overthrow
    0.60
    }}.
    0.58
     হঠাৎ
    0.58
    ანა
    0.57
    POSITIVE LOGITS
    Festival
    1.12
     festival
    1.11
     initiative
    1.10
     événement
    1.10
     Veranstaltung
    1.08
     initiatives
    1.08
     Festival
    1.07
     etkinlik
    1.06
     eventos
    1.05
     Initiatives
    1.04
    Activations Density 0.067%

    No Known Activations