© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    play and eat

    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
     extravaganza
    1.37
    oodles
    1.21
    दों
    1.16
     circumcision
    1.15
     doctr
    1.15
    LY
    1.12
    ଖ
    1.11
     লই
    1.09
    نائ
    1.09
     portent
    1.09
    POSITIVE LOGITS
    se
    0.94
    jší
    0.91
    ي
    0.86
    pone
    0.86
     re
    0.84
    意識
    0.83
     ومت
    0.81
    strictly
    0.81
     somehow
    0.80
     noc
    0.80
    Activations Density 0.001%

    No Known Activations