© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16955
    Prev
    Next
    INDEX
    Explanations

    words starting with un

    np_acts-logits-general · gemini-2.5-flash-lite

    prefix un

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xA2>
    0.40
    忉
    0.37
    臤
    0.37
    甛
    0.35
    䙲
    0.35
     सीमित
    0.34
     mediocr
    0.34
     mediocre
    0.34
    럇
    0.34
    <0xB1>
    0.34
    POSITIVE LOGITS
     un
    3.41
     Un
    3.34
    Un
    3.20
    un
    2.59
     unre
    2.55
     unm
    2.52
     uncon
    2.45
     unst
    2.45
    未
    2.44
     unf
    2.41
    Activations Density 0.818%

    No Known Activations