© 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. 34-GEMMASCOPE-RES-131K
    7. 103470
    Prev
    Next
    INDEX
    Explanations

    law of

    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
     triste
    -0.74
     Ger
    -0.69
     Keith
    -0.67
     Kel
    -0.66
    Outcome
    -0.65
    agreement
    -0.63
     funktion
    -0.63
    hlungen
    -0.63
     Chris
    -0.63
    ências
    -0.62
    POSITIVE LOGITS
     Montoya
    0.77
     Lul
    0.75
    原因
    0.73
     هفته
    0.73
    Erste
    0.71
    isierten
    0.69
     segni
    0.65
     vaksinasi
    0.65
    osse
    0.64
    Sä
    0.64
    Activations Density 0.034%

    No Known Activations