© 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. 8680
    Prev
    Next
    INDEX
    Explanations

    to summarize, justify, do, search

    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
    te
    1.24
    ist
    1.19
    據
    1.10
    rings
    1.05
    ian
    1.04
    п
    1.04
    ात
    1.00
     modern
    0.99
    度
    0.99
    rying
    0.97
    POSITIVE LOGITS
     unbedingt
    1.39
    Understand
    1.27
     assolutamente
    1.24
     nghiên
    1.23
    Considering
    1.20
    ల
    1.19
     absolument
    1.18
    𝘨
    1.18
     vadd
    1.17
    Ripe
    1.15
    Activations Density 0.102%

    No Known Activations