© 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. 60635
    Prev
    Next
    INDEX
    Explanations

    if followed by exclusion or condition

    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
    ofthe
    -1.27
     leopardo
    -1.24
    shall
    -1.13
    桠
    -1.11
    ctively
    -1.10
    佷
    -1.09
    staan
    -1.09
     centaines
    -1.09
     helicópter
    -1.06
     spise
    -1.05
    POSITIVE LOGITS
    !
    1.22
     not
    1.13
     also
    1.07
     !
    1.02
     often
    0.91
     hasn
    0.90
     hadn
    0.90
    ssaint
    0.89
     stanovnika
    0.88
     envi
    0.84
    Activations Density 0.005%

    No Known Activations