© 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. 97944
    Prev
    Next
    INDEX
    Explanations

    database query parameters

    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
    資格
    -0.82
    логических
    -0.78
    #>
    -0.77
     itemList
    -0.74
    ández
    -0.74
     whofe
    -0.72
    ラの
    -0.72
    madeus
    -0.71
     comes
    -0.70
    chemy
    -0.70
    POSITIVE LOGITS
     PDO
    1.17
     saf
    1.01
     bind
    0.88
     Bind
    0.88
    prepared
    0.86
    Param
    0.85
    saf
    0.83
    PathParam
    0.82
    把你
    0.82
     Safe
    0.81
    Activations Density 0.003%

    No Known Activations