© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    faith, rely heavily

    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
    й
    3.86
    ა
    3.59
    는
    2.98
    कीय
    2.76
    ש
    2.76
     độ
    2.75
    л
    2.67
    ب
    2.63
    ை
    2.61
    ル
    2.61
    POSITIVE LOGITS
    اً
    3.85
    𝐬
    3.76
    𝐭
    3.69
    𝐥
    3.64
    ۰۰
    3.48
    𝐩
    3.44
    𝐲
    3.43
    𝐢
    3.36
    𝐳
    3.33
    𝐝
    3.24
    Activations Density 0.536%

    No Known Activations