© 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. 82940
    Prev
    Next
    INDEX
    Explanations

    what we doing

    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
     เป็น
    -1.07
    begin
    -0.99
    も
    -0.98
     {$\
    -0.97
    Tämä
    -0.96
    IMPORTED
    -0.95
     simplement
    -0.94
    による
    -0.94
     فقط
    -0.93
    Westfalen
    -0.93
    POSITIVE LOGITS
     what
    1.51
     considers
    1.28
     doing
    1.28
     happening
    1.23
     perceive
    1.12
     thinks
    1.11
     think
    1.08
     považ
    1.07
     considered
    1.05
     contributes
    1.02
    Activations Density 0.065%

    No Known Activations