© 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. 34-GEMMASCOPE-RES-131K
    7. 76373
    Prev
    Next
    INDEX
    Explanations

    Chrome, Chromebook, Cro

    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
    样式
    -0.67
    ード
    -0.67
    姑
    -0.66
    Qin
    -0.66
    Buon
    -0.66
    nten
    -0.65
    Moll
    -0.65
    rassed
    -0.65
     buon
    -0.64
     Wied
    -0.64
    POSITIVE LOGITS
     Chrome
    1.27
     Cros
    1.23
     Cro
    1.16
     Chromebook
    1.07
     クロ
    0.97
     CRO
    0.93
    Chrome
    0.92
     Cr
    0.92
    нял
    0.90
    ondi
    0.87
    Activations Density 0.018%

    No Known Activations