© 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. 9-GEMMASCOPE-2-RES-16K
    7. 164
    Prev
    Next
    INDEX
    Explanations

    public Minecraft, global name

    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_9_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
    o
    1.28
    on
    1.12
    ی
    1.10
    𝙤
    1.08
    𝙈
    1.08
    𝙋
    1.08
    𝙪
    1.06
    }))
    1.04
    ishwarya
    1.03
    rsi
    1.03
    POSITIVE LOGITS
     simplifié
    1.25
    facing
    1.11
    ګ
    1.09
     expectancy
    1.08
     vistos
    1.07
     gestaltet
    1.06
    ită
    1.05
    讧
    1.03
     viendo
    1.03
     tiver
    1.03
    Activations Density 1.114%

    No Known Activations