© 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. 10-GEMMASCOPE-RES-131K
    7. 119810
    Prev
    Next
    INDEX
    Explanations

    evaluations followed by infinitive 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
     your
    -1.84
     \&
    -1.41
     those
    -1.39
     querer
    -1.38
     it
    -1.37
     yeni
    -1.37
     new
    -1.35
     there
    -1.35
     different
    -1.35
     various
    -1.30
    POSITIVE LOGITS
     estadounid
    1.41
     jl
    1.39
     vee
    1.35
     polie
    1.35
     POSSIBLE
    1.34
     parms
    1.33
    6
    1.30
     qa
    1.29
     catast
    1.29
     UNIVERS
    1.28
    Activations Density 0.021%

    No Known Activations