© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7607
    Prev
    Next
    INDEX
    Explanations

    adverb + to/preposition phrases

    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
     största
    -2.13
     också
    -2.11
     basteln
    -1.98
    亙
    -1.98
     intolerable
    -1.96
    也可
    -1.95
     sécher
    -1.86
     laughable
    -1.83
     of
    -1.82
     unbearable
    -1.80
    POSITIVE LOGITS
     you
    2.38
    彞
    2.23
     is
    2.16
    
    2.08
     manfaat
    2.08
    tine
    2.02
     complemented
    2.00
     don
    1.97
    Ꭳ
    1.94
    borderSide
    1.91
    Activations Density 0.123%

    No Known Activations