© 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. 111116
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or articles

    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
     "
    -1.49
     verbreitet
    -1.43
     "[
    -1.40
     kurzem
    -1.39
     ''
    -1.39
    _
    -1.38
     isn
    -1.38
     doesn
    -1.34
     demselben
    -1.29
     verfolgt
    -1.27
    POSITIVE LOGITS
     in
    1.79
     of
    1.75
    Durata
    1.43
     iſt
    1.38
    sehr
    1.30
    欸
    1.26
    semester
    1.26
    艸
    1.25
     nadru
    1.25
     with
    1.24
    Activations Density 0.008%

    No Known Activations