© 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. 111553
    Prev
    Next
    INDEX
    Explanations

    information disclosure, solution, published, of course, election, scoreless, begin

    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
     
    -2.88
    E
    -2.83
    N
    -2.42
    D
    -2.33
    A
    -2.25
     disparate
    -2.22
    u
    -2.19
    S
    -2.19
    b
    -2.17
    :
    -2.17
    POSITIVE LOGITS
    瞜
    2.84
    縂
    2.78
    轳
    2.70
    呖
    2.69
    actéristi
    2.67
     現貨
    2.56
    豋
    2.48
    袮
    2.47
     emporio
    2.38
     合集
    2.34
    Activations Density 0.002%

    No Known Activations