© 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
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 576
    Prev
    Next
    INDEX
    Explanations

    prominent Jamaican politicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     Бан
    1.05
    Neurons
    1.04
    𒂗
    1.03
     യുവാ
    1.02
     cihaz
    1.02
     Lehenga
    1.01
    Technologies
    1.01
    稩
    1.01
    Alert
    1.01
    愪
    1.01
    POSITIVE LOGITS
     generic
    0.66
     non
    0.65
     individual
    0.62
     these
    0.62
     successful
    0.62
     active
    0.60
     bear
    0.57
     primary
    0.55
     adult
    0.55
     golf
    0.55
    Activations Density 10.596%

    No Known Activations