© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2583
    Prev
    Next
    INDEX
    Explanations

    the + technical nouns

    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_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
    ×
    1.55
     heights
    1.39
    鐗
    1.36
     Дру
    1.33
     dependents
    1.33
     anak
    1.32
     D
    1.31
     zusätzlichen
    1.30
     ama
    1.29
            
    1.29
    POSITIVE LOGITS
     lucru
    1.67
    sheet
    1.52
     culminating
    1.47
    𝐲
    1.47
    ction
    1.45
     diagonalization
    1.44
     trialComponents
    1.44
    throttle
    1.43
    뀌
    1.42
    <unused312>
    1.42
    Activations Density 0.266%

    No Known Activations