© 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. 34-GEMMASCOPE-RES-131K
    7. 107756
    Prev
    Next
    INDEX
    Explanations

    to plus 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_34/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
     bacio
    -0.97
     Konkur
    -0.92
     interacting
    -0.91
     preescolar
    -0.90
     다른
    -0.89
     prenotazione
    -0.88
    summon
    -0.87
     ()=>
    -0.86
    就是要
    -0.86
    そこ
    -0.85
    POSITIVE LOGITS
     help
    1.43
    ช่วย
    1.33
     помочь
    1.19
    help
    1.18
     come
    1.02
     join
    1.00
     suyo
    1.00
     borrow
    0.97
     попробовать
    0.95
     CiNii
    0.94
    Activations Density 0.055%

    No Known Activations