© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8117
    Prev
    Next
    INDEX
    Explanations

    annual

    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
    
    2.49
     dint
    2.11
    स
    2.10
    
    2.09
    lardan
    1.89
    р
    1.88
     templ
    1.85
    ě
    1.85
    larni
    1.82
    💨
    1.81
    POSITIVE LOGITS
    er
    2.45
    стью
    2.04
    idades
    2.00
    ার
    1.99
    ties
    1.88
    thm
    1.88
    nya
    1.84
    mselves
    1.81
    sanitize
    1.80
    tained
    1.77
    Activations Density 0.064%

    No Known Activations