© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9787
    Prev
    Next
    INDEX
    Explanations

    Siem Reap, Norman Conquest, Oklahoma

    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_9_width_262k_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
     covariate
    3.04
    ів
    2.65
    \{
    2.63
    馳
    2.63
    ల
    2.63
    𝓌
    2.62
     دارای
    2.56
    р
    2.54
     المقد
    2.54
     parseInt
    2.50
    POSITIVE LOGITS
    ा
    3.12
    та
    3.11
    लिये
    2.89
    
    2.84
    UARY
    2.83
    ர்
    2.81
    Aaj
    2.78
    
    2.75
    घर
    2.73
    те
    2.71
    Activations Density 0.056%

    No Known Activations