© 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. 123959
    Prev
    Next
    INDEX
    Explanations

    going to 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
    bringer
    -1.66
     takk
    -1.63
     stik
    -1.55
     ganger
    -1.46
    蜗
    -1.45
    
    -1.39
     PUSTAKA
    -1.39
     arată
    -1.38
    parken
    -1.38
     damen
    -1.37
    POSITIVE LOGITS
    〒
    1.51
    jenige
    1.47
    を見た
    1.41
     lourd
    1.41
    jenigen
    1.39
    の問題
    1.39
    hado
    1.38
    俺は
    1.38
     réve
    1.37
    вого
    1.36
    Activations Density 0.015%

    No Known Activations