© 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. 12819
    Prev
    Next
    INDEX
    Explanations

    Deutsche Bank, Rusty Mug, spontaneous emission

    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
    
    1.13
     WAS
    1.10
    '/
    1.10
     znajdują
    1.10
     courtesy
    1.08
    你在
    1.08
     majd
    1.08
    
    1.07
    
    1.07
    er
    1.06
    POSITIVE LOGITS
     dàng
    1.35
    в
    1.28
     topological
    1.25
    ونَ
    1.23
    МІ
    1.22
    ל
    1.21
     cancé
    1.20
     bran
    1.20
    sing
    1.19
     toxicity
    1.18
    Activations Density 0.009%

    No Known Activations