© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3836
    Prev
    Next
    INDEX
    Explanations

    sports teams and fan bases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    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
     является
    0.73
     Smithsonian
    0.63
     facilitates
    0.62
     влияет
    0.61
     enables
    0.61
     underlies
    0.60
    
    0.59
     assists
    0.59
     eignet
    0.57
     указывает
    0.57
    POSITIVE LOGITS
    队
    0.73
     fanáticos
    0.64
     equipos
    0.64
     फैंस
    0.64
     फैन्स
    0.63
    attaque
    0.61
     squadra
    0.60
     అభిమా
    0.59
    팬
    0.58
    forever
    0.57
    Activations Density 0.044%

    No Known Activations