© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12611
    Prev
    Next
    INDEX
    Explanations

    夫妻肺片 recipe/description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    
    0.75
    ...</
    0.75
    !</
    0.70
    ..."
    0.68
     Arik
    0.68
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.68
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.67
    :\\
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.64
    POSITIVE LOGITS
     Commence
    1.12
     což
    1.05
     plateforme
    0.94
     seinem
    0.94
     Allowing
    0.92
     propel
    0.91
     Sebuah
    0.90
     Describes
    0.90
     zentrale
    0.90
    čkom
    0.89
    Activations Density 0.004%

    No Known Activations