© 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. 91479
    Prev
    Next
    INDEX
    Explanations

    subject followed by modal or auxiliary verb

    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
    我们可以
    -1.32
    我們
    -1.23
    ✦
    -1.07
    我们
    -1.05
     możemy
    -1.03
    nye
    -0.97
    dieron
    -0.95
    Then
    -0.95
    nae
    -0.94
     says
    -0.93
    POSITIVE LOGITS
     would
    3.44
     was
    3.30
     had
    2.56
     will
    2.16
     could
    1.96
     hadn
    1.92
     needed
    1.85
     pihaknya
    1.62
     había
    1.61
     wasn
    1.58
    Activations Density 0.052%

    No Known Activations