© 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. 48074
    Prev
    Next
    INDEX
    Explanations

    Q: followed by question/topic

    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
     because
    -0.91
    Have
    -0.91
     to
    -0.87
     despite
    -0.84
     can
    -0.84
    Quite
    -0.84
     Quite
    -0.84
     viera
    -0.84
     their
    -0.83
     could
    -0.83
    POSITIVE LOGITS
     Besitz
    1.03
     invece
    1.02
    []){
    1.01
     시작
    1.00
    iscus
    0.99
     aquello
    0.98
    rophes
    0.96
    ∖
    0.96
     bevorzug
    0.93
     zerst
    0.92
    Activations Density 0.000%

    No Known Activations