© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2206
    Prev
    Next
    INDEX
    Explanations

    window/windows

    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
    ad
    3.08
    ete
    2.97
    er
    2.89
    ाह
    2.87
    end
    2.86
    ども
    2.82
    ात
    2.80
    ̣
    2.73
    اً
    2.72
    up
    2.72
    POSITIVE LOGITS
    pane
    3.42
     arresting
    3.35
     plasticity
    3.23
    ε
    3.07
    ≐
    3.02
    𝐵
    3.01
    什么是
    2.91
     fibroblast
    2.91
    しかし
    2.91
     그러나
    2.87
    Activations Density 0.303%

    No Known Activations