© 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. 22-GEMMASCOPE-RES-131K
    7. 35782
    Prev
    Next
    INDEX
    Explanations

    modal dialog prompts

    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_22/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
    
    -0.96
    (©
    -0.93
     kors
    -0.93
     bienvenue
    -0.92
    tried
    -0.91
    ividual
    -0.91
     Seizures
    -0.91
    太过
    -0.90
    sprit
    -0.90
    ști
    -0.90
    POSITIVE LOGITS
    BUTTON
    1.12
    ٱ
    0.91
    YesNo
    0.90
    ５
    0.90
    إذا
    0.90
     decision
    0.90
    ถ้า
    0.89
    ８
    0.88
     przeprowad
    0.87
    本人
    0.86
    Activations Density 0.002%

    No Known Activations