© 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. 32101
    Prev
    Next
    INDEX
    Explanations

    module, license, version

    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
    他知道
    -1.16
    要不然
    -1.13
    说实话
    -1.04
    因为他
    -1.04
    seems
    -1.04
     minimalista
    -0.99
    这下
    -0.93
     turco
    -0.93
    轰隆
    -0.93
    他现在
    -0.93
    POSITIVE LOGITS
     therefore
    2.69
     Moreover
    2.58
     moreover
    2.55
    Moreover
    2.44
     поэтому
    2.31
    Therefore
    2.30
     Therefore
    2.22
     furthermore
    2.16
     even
    2.13
     Furthermore
    2.03
    Activations Density 0.002%

    No Known Activations