© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42078
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun phrase

    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
    if
    -1.58
     if
    -1.51
    !(
    -1.47
    that
    -1.32
     hvis
    -1.25
     "")
    
    -1.20
    !
    -1.19
    泺
    -1.18
     delin
    -1.16
    ll
    -1.15
    POSITIVE LOGITS
     rövid
    1.55
     dipinto
    1.54
     sogenannten
    1.48
     informieren
    1.47
     giudice
    1.45
     gelernt
    1.44
    ཨ
    1.42
     Pläne
    1.41
     reparación
    1.41
     üblichen
    1.38
    Activations Density 0.274%

    No Known Activations