© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    pembrolizumab

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

    understanding modifications and improvements

    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
    ]
    0.52
     through
    0.51
     Vice
    0.49
    infused
    0.49
     invited
    0.48
     costs
    0.47
    value
    0.47
     filled
    0.46
     Friday
    0.46
     Christine
    0.45
    POSITIVE LOGITS
    蛔
    0.50
    제가
    0.50
     ########.
    0.50
    ائِ
    0.47
     calme
    0.47
    
    0.46
    ಎ
    0.46
    Произ
    0.46
    ്രാ
    0.46
    立
    0.46
    Activations Density 0.000%

    No Known Activations