© 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. 13015
    Prev
    Next
    INDEX
    Explanations

    technical indicators

    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
    edic
    1.06
     Paglinawan
    1.01
    
    0.99
    eil
    0.96
    edics
    0.95
    ০
    0.94
    achadh
    0.91
    itattu
    0.90
     pukul
    0.90
     ਘ
    0.90
    POSITIVE LOGITS
    𝖊
    1.01
     meager
    0.97
    챙
    0.96
    Bins
    0.91
    šie
    0.91
    সম্প
    0.89
    agner
    0.89
    পালা
    0.88
    gang
    0.88
    можно
    0.88
    Activations Density 0.010%

    No Known Activations