© 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. 9-GEMMASCOPE-2-RES-16K
    7. 582
    Prev
    Next
    INDEX
    Explanations

    rapidly changing trends

    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_9_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
    worldly
    1.63
    cules
    1.46
    wounded
    1.43
    AIN
    1.41
    grund
    1.41
     jokingly
    1.40
    र
    1.39
    дан
    1.33
    =}
    1.31
     aanv
    1.30
    POSITIVE LOGITS
     mundial
    2.29
     trends
    2.20
     mondiale
    1.99
     qualit
    1.96
     proliferation
    1.93
     suicides
    1.88
     industria
    1.83
     influx
    1.83
     crescendo
    1.82
     internazionale
    1.80
    Activations Density 3.258%

    No Known Activations