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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    bowl, muffins, Existence, oligodendrocytes, Heidegger, Aegean, shirts

    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
    م
    1.59
    یه
    1.13
    ين
    1.11
     davon
    1.06
     lactis
    1.05
    ০
    1.02
    को
    1.02
    කි
    1.01
     mari
    1.00
     adulter
    1.00
    POSITIVE LOGITS
    ls
    1.16
     воздуха
    1.08
    chos
    1.05
    ϲ
    1.04
    nment
    1.02
    ⎛
    1.00
    lstm
    0.95
    cb
    0.94
    zymy
    0.93
    ర్రీ
    0.92
    Activations Density 0.109%

    No Known Activations