© 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. 29-GEMMASCOPE-2-RES-16K
    7. 833
    Prev
    Next
    INDEX
    Explanations

    mountainous tasks

    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_29_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
     Nickelodeon
    0.86
     ciudades
    0.85
    衙
    0.83
     மெட்ரோ
    0.82
     Roblox
    0.82
    WWE
    0.82
     மாநக
    0.81
     TypeScript
    0.80
    廉
    0.80
    Street
    0.79
    POSITIVE LOGITS
     hiking
    2.36
     hike
    2.32
     hikers
    2.24
     Hiking
    2.23
    Hiking
    2.22
     mountaine
    2.21
     hikes
    2.14
     Hike
    2.12
     hiker
    2.11
     mountain
    2.04
    Activations Density 0.541%

    No Known Activations