© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9950
    Prev
    Next
    INDEX
    Explanations

    was a

    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
    indruck
    1.06
    몄
    0.90
     intermédiaire
    0.88
     indebtedness
    0.88
     Aufgrund
    0.87
     Компания
    0.86
     magyar
    0.86
    绎
    0.85
     linewidth
    0.84
     Footage
    0.83
    POSITIVE LOGITS
    uil
    1.20
     charming
    1.17
     discontinue
    1.12
    Anime
    1.08
    healing
    1.05
    ude
    1.03
    styles
    1.02
    Aloe
    1.01
    variants
    1.01
    chine
    1.01
    Activations Density 0.001%

    No Known Activations