© 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. 75457
    Prev
    Next
    INDEX
    Explanations

    Turkish words and suffixes

    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
    いため
    -1.04
     incluindo
    -1.02
     znam
    -1.02
     Após
    -0.99
     GUY
    -0.91
    もも
    -0.90
     ATLANTIC
    -0.88
     CONFERENCE
    -0.88
    дук
    -0.86
     incluyen
    -0.85
    POSITIVE LOGITS
     a
    1.94
     an
    1.49
     being
    1.31
    ness
    1.22
     be
    1.13
    ly
    1.11
     manner
    1.11
     şekilde
    1.09
     olarak
    1.09
     been
    1.05
    Activations Density 0.002%

    No Known Activations