© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9351
    Prev
    Next
    INDEX
    Explanations

    dispose, disposal, disposition, fate

    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
    s
    2.76
     
    2.58
    াই
    2.49
     FormsModule
    2.41
    ږي
    2.38
    ам
    2.30
    ্ত
    2.29
    ्स
    2.27
    ы
    2.27
    ʟ
    2.24
    POSITIVE LOGITS
    ので
    2.86
    此之外
    2.73
    ن
    2.72
    HING
    2.68
     jazdy
    2.64
    ch
    2.55
     Equipped
    2.46
     vững
    2.45
    الأ
    2.40
    e
    2.40
    Activations Density 0.054%

    No Known Activations