© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7558
    Prev
    Next
    INDEX
    Explanations

    Sunday

    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_22_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
     nitidus
    0.98
     voj
    0.92
     fert
    0.87
    codon
    0.87
     відповід
    0.87
     leto
    0.86
    崚
    0.86
    ബു
    0.84
     stargazer
    0.84
     miRNAs
    0.83
    POSITIVE LOGITS
    Fund
    1.09
    fund
    1.02
     Fund
    0.97
     Brunch
    0.89
    accordo
    0.84
    പരി
    0.79
     पौधा
    0.78
    الله
    0.78
     fund
    0.77
     Grafton
    0.77
    Activations Density 0.058%

    No Known Activations