© 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. 10-GEMMASCOPE-RES-131K
    7. 40382
    Prev
    Next
    INDEX
    Explanations

    very soon, shortly, recently, easy, close, simple

    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
     “,
    -1.54
    来找
    -1.53
     thingy
    -1.52
     leds
    -1.52
     riu
    -1.51
    猡
    -1.49
     morm
    -1.48
     Portugu
    -1.48
     イラストレーション
    -1.48
    橚
    -1.45
    POSITIVE LOGITS
    this
    1.76
    開始
    1.64
    :
    1.62
     dotyczą
    1.59
    呦
    1.52
     Our
    1.52
     Yeah
    1.52
    """
    1.52
    真的很
    1.48
     jeopardize
    1.47
    Activations Density 0.024%

    No Known Activations