© 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. 50215
    Prev
    Next
    INDEX
    Explanations

    names of media franchises

    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
    idoscope
    -0.87
     intra
    -0.81
     waar
    -0.79
    ناعة
    -0.79
    UPD
    -0.78
     efter
    -0.77
     Mord
    -0.75
    Тарих
    -0.75
    vellous
    -0.75
     recommand
    -0.74
    POSITIVE LOGITS
    ждане
    0.81
     Bleeding
    0.81
    ῷ
    0.79
    arsh
    0.79
     sequences
    0.77
     जबकि
    0.77
    
    0.76
    illier
    0.76
    iterations
    0.75
     کت
    0.75
    Activations Density 0.003%

    No Known Activations