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. 7680
    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
     γ
    0.69
     sua
    0.67
     daarna
    0.65
     ideological
    0.64
    .
    0.63
    ために
    0.63
    leep
    0.61
     feminist
    0.61
    ℓ
    0.59
    blog
    0.58
    POSITIVE LOGITS
     forklift
    0.96
     powertrain
    0.93
    <unused1724>
    0.90
     Fahrzeug
    0.90
     নারায়ণগঞ্জ
    0.89
     xWidth
    0.88
     Chassis
    0.87
    Vehicle
    0.85
    车辆
    0.84
     йөкләү
    0.83
    Activations Density 0.001%

    No Known Activations