© 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. 59041
    Prev
    Next
    INDEX
    Explanations

    package Ice;

    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
    SetId
    -0.80
    chufe
    -0.71
     Set
    -0.70
     gesetzt
    -0.67
     アク
    -0.65
    Mesa
    -0.64
    Set
    -0.64
    ディズニー
    -0.64
     Juego
    -0.63
     Medusa
    -0.63
    POSITIVE LOGITS
     שלה
    0.69
    
    0.67
     Electrical
    0.66
    alist
    0.65
    onnay
    0.63
    恐怖
    0.62
     молеку
    0.62
     Developing
    0.62
    ←
    0.61
    zir
    0.61
    Activations Density 0.061%

    No Known Activations