© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    support ticketing policies

    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
    ن
    1.84
    ך
    1.29
    貸款
    1.27
    lijke
    1.26
    ตรฐาน
    1.18
    fand
    1.16
    <bos>
    1.15
     daj
    1.14
     oats
    1.14
    convex
    1.12
    POSITIVE LOGITS
    𝑖
    1.51
    𝑎
    1.45
    ड
    1.43
    ⁩
    1.35
    𝐷
    1.33
    ्स
    1.32
    𝐶
    1.31
    𝑋
    1.29
    𝑑
    1.28
    />}
    1.26
    Activations Density 0.175%

    No Known Activations