© 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. 568
    Prev
    Next
    INDEX
    Explanations

    negative assertion

    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
     fictitious
    1.89
    󠁢
    1.88
     ctypes
    1.86
    xadmin
    1.84
     perks
    1.83
     hierarchical
    1.80
     grammaticality
    1.78
    ocurrencies
    1.78
     raha
    1.77
    لیفون
    1.77
    POSITIVE LOGITS
    𝒊
    2.07
    اک
    1.98
    𝒐
    1.94
    های
    1.90
    లు
    1.89
    من
    1.86
    𝒆
    1.86
    噌
    1.85
    ുടെ
    1.84
    izing
    1.80
    Activations Density 6.770%

    No Known Activations