© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 131035
    Prev
    Next
    INDEX
    Explanations

    не ... (Russian negation verb)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elever
    -1.41
     flyg
    -1.32
    Zhou
    -1.27
     årets
    -1.26
     奶油
    -1.25
     onu
    -1.24
     cirka
    -1.23
     eene
    -1.21
    therefore
    -1.20
    ræ
    -1.18
    POSITIVE LOGITS
     would
    1.81
     podremos
    1.54
     tendremos
    1.48
     müßte
    1.46
     before
    1.45
     could
    1.45
     are
    1.43
     various
    1.40
     acudir
    1.39
    因为他
    1.39
    Activations Density 0.009%

    No Known Activations