© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    ROBOT, Bessie

    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
    šu
    1.01
     farklı
    0.99
    гато
    0.98
     др
    0.97
    🔝
    0.97
    📩
    0.95
    📊
    0.94
    💪
    0.94
    示例
    0.94
    どのような
    0.93
    POSITIVE LOGITS
     hilarious
    1.43
     wacky
    1.24
     toilet
    1.21
     furiously
    1.21
     corpses
    1.17
     weird
    1.17
     proletariat
    1.15
     hideous
    1.13
     booze
    1.12
     comedy
    1.12
    Activations Density 0.454%

    No Known Activations