© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4647
    Prev
    Next
    INDEX
    Explanations

    business terms

    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_17_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
     ಆದರೆ
    1.28
     ಅನ್ನು
    1.18
    ਨ
    1.15
     છે
    1.11
     propositional
    1.06
    pherd
    1.04
     languages
    1.01
     تعدى
    1.01
     posso
    0.99
     ternary
    0.99
    POSITIVE LOGITS
    ＆
    1.17
    
    1.12
    器
    1.12
    த்தின்
    1.11
    中心
    1.10
     एवं
    1.10
    三十
    1.09
    த்
    1.08
    信息
    1.07
    情報
    1.06
    Activations Density 0.025%

    No Known Activations