© 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. 102483
    Prev
    Next
    INDEX
    Explanations

    end of code execution

    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
    迁移
    -0.86
     hogar
    -0.81
    𝑫
    -0.80
    mutter
    -0.79
    feste
    -0.78
    Amicalement
    -0.78
    Institut
    -0.77
    tempuran
    -0.76
    ambung
    -0.75
    Alors
    -0.72
    POSITIVE LOGITS
     exit
    2.42
    exit
    2.38
     die
    2.22
    die
    2.13
     died
    1.81
     Die
    1.61
     dies
    1.59
     DIE
    1.49
     Exit
    1.45
     dying
    1.43
    Activations Density 0.012%

    No Known Activations