© 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-16K
    7. 195
    Prev
    Next
    INDEX
    Explanations

    numbers 2

    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
     doom
    1.58
    ların
    1.47
    ্ড
    1.43
    barung
    1.41
     mistaken
    1.41
     Oriental
    1.39
     misconception
    1.37
    ്
    1.35
    larına
    1.34
     esté
    1.34
    POSITIVE LOGITS
    nd
    2.84
    ت
    2.63
    ת
    2.18
    ي
    2.07
     thirds
    2.04
    ed
    2.02
    thirds
    1.92
    า
    1.90
    т
    1.76
    ة
    1.73
    Activations Density 0.551%

    No Known Activations