© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    . followed by 0 or index

    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
    raž
    1.35
     wasting
    1.18
    ्यु
    1.15
    <0x8F>
    1.10
    fälle
    1.08
    加熱
    1.08
    ణం
    1.03
    ியின்
    1.03
    itumor
    1.01
    бору
    1.00
    POSITIVE LOGITS
    د
    1.22
     inventories
    1.21
    ই
    1.21
    Nella
    1.19
     umani
    1.15
    ›
    1.12
     illum
    1.12
     humains
    1.10
     ascent
    1.10
    ▶
    1.07
    Activations Density 0.003%

    No Known Activations