© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112452
    Prev
    Next
    INDEX
    Explanations

    being subjected to

    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_10/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
    饽
    -1.56
    leſs
    -1.55
    ības
    -1.55
    原始内容存档于
    -1.55
    忉
    -1.52
    萄
    -1.49
    犄
    -1.48
     greateſt
    -1.47
    祧
    -1.46
    🌰
    -1.45
    POSITIVE LOGITS
    ↵
    2.69
    1
    2.00
     \\
    1.80
    6
    1.77
    year
    1.77
    9
    1.73
     également
    1.61
     преимущества
    1.58
     subject
    1.57
     WITH
    1.56
    Activations Density 0.033%

    No Known Activations