© 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. 3028
    Prev
    Next
    INDEX
    Explanations

    promoting development and improvement

    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
     ketika
    1.16
     ह्या
    0.96
     या
    0.94
    फ़
    0.94
     seems
    0.94
     Ketika
    0.92
    +
    0.92
     +
    0.91
     biasa
    0.90
    angnya
    0.89
    POSITIVE LOGITS
     fomentar
    1.40
     elevar
    1.32
     curbing
    1.28
    ందన్నారు
    1.20
     conducive
    1.19
     fostering
    1.16
     fortalecer
    1.16
     establecidos
    1.15
     जागर
    1.14
     améliorer
    1.14
    Activations Density 0.029%

    No Known Activations