© 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. 10037
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by locations or actions

    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
    ꪻ
    -1.52
    помним
    -1.52
    ൮
    -1.49
     beaucoup
    -1.48
    ᨕ
    -1.47
    翃
    -1.47
     also
    -1.45
    salms
    -1.45
    opardi
    -1.41
    CDT
    -1.41
    POSITIVE LOGITS
     this
    1.94
     there
    1.48
     aktuellen
    1.46
    '
    1.45
     they
    1.40
     gesamten
    1.37
     ursprünglichen
    1.30
     klassischen
    1.27
     each
    1.26
     umfass
    1.25
    Activations Density 0.155%

    No Known Activations