© 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. 10-GEMMASCOPE-RES-131K
    7. 41445
    Prev
    Next
    INDEX
    Explanations

    waterproof and bulletproof

    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
     `
    -2.39
     Когда
    -2.33
     When
    -2.13
     tattered
    -2.11
    ⟣
    -2.08
     Quando
    -2.06
     Cuando
    -2.05
    珦
    -2.00
     ``
    -1.97
     dritten
    -1.95
    POSITIVE LOGITS
    s
    3.41
    ی
    2.58
    proof
    2.48
    ’
    2.47
    ed
    2.36
    Then
    2.33
     biedt
    2.31
    🫘
    2.22
     atau
    2.14
    this
    2.11
    Activations Density 0.001%

    No Known Activations