© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    Here's why

    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
    ть
    2.90
    م
    2.87
    h
    2.62
    ب
    2.56
    ת
    2.35
    er
    2.28
    ة
    2.19
    ים
    2.18
    ر
    2.16
    ्स
    2.13
    POSITIVE LOGITS
     reluctant
    2.41
    되는
    2.23
     veneer
    2.09
    ᴏ
    2.07
    ᴇ
    2.06
    มาจาก
    2.05
    ISTICS
    2.03
    setTo
    2.02
    িকপ্ট
    2.02
     قلي
    1.98
    Activations Density 0.139%

    No Known Activations