© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129773
    Prev
    Next
    INDEX
    Explanations

    Ground Zero, Q:, Turkey’s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ādi
    -1.06
    ✨:
    -1.02
     EVENTS
    -1.02
    
    -1.00
     lettre
    -0.99
    xmax
    -0.97
    }):
    -0.97
    ฿
    -0.96
    tség
    -0.96
    Ω
    -0.96
    POSITIVE LOGITS
     sogar
    1.00
    élène
    1.00
    illium
    0.98
     према
    0.98
    ENIX
    0.97
     thậm
    0.97
    EFAULT
    0.95
    Conclusão
    0.92
    zaar
    0.92
    Même
    0.91
    Activations Density 0.000%

    No Known Activations