© 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. 8920
    Prev
    Next
    INDEX
    Explanations

    breed, yield, male, mentor, minerals

    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
     laces
    1.25
    ꯕ
    1.22
    erce
    1.15
     termini
    1.15
    ीजन
    1.14
    ทาง
    1.11
    很多的
    1.11
    یل
    1.09
    𝖐
    1.09
    맟
    1.08
    POSITIVE LOGITS
    nh
    1.26
    сть
    1.24
    ils
    1.15
    多い
    1.13
    ことが
    1.12
    𝑻
    1.12
     উদ্দেশে
    1.09
    েন্দ
    1.09
    hed
    1.07
    ことができる
    1.06
    Activations Density 0.000%

    No Known Activations