© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    territorial annexations

    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
     대로
    1.38
    ри
    1.37
    ك
    1.32
    ка
    1.32
    يات
    1.31
     вещи
    1.29
    ку
    1.26
    िलं
    1.23
    ০০
    1.23
    ный
    1.21
    POSITIVE LOGITS
    દ
    1.12
     reformas
    1.10
    Hud
    1.06
     bolas
    1.06
    Dance
    1.04
    苳
    1.01
    ยอด
    1.01
    AIS
    1.00
    Forg
    1.00
    IDC
    0.99
    Activations Density 0.000%

    No Known Activations