© 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-262K
    7. 12055
    Prev
    Next
    INDEX
    Explanations

    rapid action

    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_262k_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
    ر
    4.22
    ل
    4.05
    र
    3.43
    رین
    3.20
    ার
    3.18
    म
    3.13
    ੍ਹ
    3.01
    ۰
    2.87
    ്
    2.79
     excellently
    2.77
    POSITIVE LOGITS
    𝒅
    3.61
    𝒌
    3.29
    𝒂
    3.27
    𝒍
    3.23
    𝒔
    3.19
    a
    3.06
    𝒎
    3.01
    𝒕
    2.81
    𝒙
    2.80
    ture
    2.76
    Activations Density 0.025%

    No Known Activations