© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 196851
    Prev
    Next
    INDEX
    Explanations

    constructs, figures, brands

    np_acts-logits-general · gemini-2.5-flash-lite

    computational components and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    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
    terminus
    0.50
    ದ್
    0.46
     ነው።
    0.46
    ವಾಸ
    0.45
    દય
    0.45
    
    0.44
     inspirado
    0.44
    esistenza
    0.44
    ಲ್
    0.43
     Itália
    0.43
    POSITIVE LOGITS
     to
    0.52
     has
    0.47
     formatted
    0.45
     Moderate
    0.45
     Suzuki
    0.43
     Gallery
    0.43
     panel
    0.42
     Recommended
    0.41
    ضبط
    0.41
    捛
    0.41
    Activations Density 0.001%

    No Known Activations