© 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. 115713
    Prev
    Next
    INDEX
    Explanations

    day/time announcements

    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
     PARAMETERS
    -0.90
    Koordinaten
    -0.89
     mainan
    -0.85
    parameters
    -0.83
    ❤️❤️❤️
    -0.82
    rcParams
    -0.82
    ."<
    -0.82
     GAMES
    -0.80
    mappedBy
    -0.79
    estre
    -0.78
    POSITIVE LOGITS
    Begin
    1.08
     Begin
    0.95
     #
    0.81
     benefic
    0.79
     TEM
    0.79
    #
    0.79
     adhe
    0.75
     await
    0.74
    argentina
    0.74
     recarg
    0.73
    Activations Density 0.000%

    No Known Activations