© 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. 34-GEMMASCOPE-RES-131K
    7. 32502
    Prev
    Next
    INDEX
    Explanations

    in phrases like "in production" or "in favour"

    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
     placement
    -0.94
     место
    -0.93
     possibilities
    -0.89
     Ahnung
    -0.85
     eventual
    -0.85
    place
    -0.84
     места
    -0.84
     bidra
    -0.82
    场所
    -0.82
     possibility
    -0.82
    POSITIVE LOGITS
     accordance
    0.90
    itatis
    0.89
    の絵
    0.85
    感染
    0.85
     CreateTagHelper
    0.76
    xtures
    0.76
     схо
    0.76
    duğu
    0.75
    <0x8F>
    0.75
    כל
    0.74
    Activations Density 0.011%

    No Known Activations