© 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. 85064
    Prev
    Next
    INDEX
    Explanations

    phrases starting with prepositions

    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
     första
    -1.68
     '-';
    -1.60
    ができ
    -1.39
     SAME
    -1.38
     της
    -1.36
     He
    -1.35
     aasta
    -1.32
    痦
    -1.31
     to
    -1.30
    级的
    -1.30
    POSITIVE LOGITS
    宬
    1.59
    媗
    1.52
    槼
    1.52
    珢
    1.51
    FailureListener
    1.51
     différent
    1.48
    昞
    1.45
     filles
    1.41
    your
    1.41
     different
    1.40
    Activations Density 0.119%

    No Known Activations