© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85965
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     and
    -1.78
     
    -1.71
     “
    -1.54
     new
    -1.45
     but
    -1.30
    ).
    -1.30
    ()
    -1.27
     =
    -1.21
     ,
    -1.20
     C
    -1.18
    POSITIVE LOGITS
    We
    1.49
     its
    1.47
     mostrarán
    1.46
     namin
    1.45
     anderer
    1.43
     다른
    1.41
     expects
    1.40
     isn
    1.38
     tasca
    1.38
     bardziej
    1.35
    Activations Density 0.050%

    No Known Activations