© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48872
    Prev
    Next
    INDEX
    Explanations

    mathematical and database tables

    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
     近
    -0.84
    近
    -0.83
     пальто
    -0.78
     fortal
    -0.77
    ط
    -0.77
    ！！”
    -0.75
    Net
    -0.72
    祥
    -0.71
    ists
    -0.71
     Gedanke
    -0.70
    POSITIVE LOGITS
    一開始
    0.78
    的机会
    0.77
    endeu
    0.76
    ثمار
    0.75
    一點
    0.75
    剛剛
    0.74
    overe
    0.74
    олові
    0.73
     productividad
    0.72
     Exhibitions
    0.71
    Activations Density 0.003%

    No Known Activations