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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 8341
    Prev
    Next
    INDEX
    Explanations

    send permalink font classes layers WIN iam SECRET

    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
    े
    0.76
    {}".
    0.73
    Modules
    0.66
    {}",
    0.65
    ेलर
    0.65
     Landmarks
    0.64
     Simulation
    0.64
    รอ
    0.63
    ﺑ
    0.63
     Policy
    0.63
    POSITIVE LOGITS
    𝓎
    0.75
     
    0.74
    কাতা
    0.72
     revers
    0.66
     jeruk
    0.64
     pues
    0.64
    
    0.62
     
    0.61
     typeface
    0.60
    
    0.60
    Activations Density 0.078%

    No Known Activations