© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84243
    Prev
    Next
    INDEX
    Explanations

    prepositions and prefixes with names

    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_34/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
     และ
    -0.83
     broader
    -0.80
    labelText
    -0.78
     ({
    -0.78
    arza
    -0.77
     perchance
    -0.76
    Ich
    -0.75
     (&
    -0.75
     ابتد
    -0.74
     ลิ
    -0.73
    POSITIVE LOGITS
    謠
    1.03
     σήμερα
    0.95
    してみた
    0.91
     így
    0.89
     so
    0.86
    zf
    0.84
    ୈ
    0.82
    unzione
    0.81
    ப்பட்டது
    0.79
    styrelsen
    0.78
    Activations Density 0.036%

    No Known Activations