© 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. 65134
    Prev
    Next
    INDEX
    Explanations

    Emile, Rousseau, Julie

    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
    édi
    -0.81
    也不是
    -0.81
    Ἅ
    -0.75
    Obama
    -0.70
    posób
    -0.69
    Lib
    -0.68
    辙
    -0.68
     轮
    -0.65
    pov
    -0.64
    TargetApi
    -0.64
    POSITIVE LOGITS
     Discourse
    1.10
     Emile
    1.02
     Savoy
    0.88
     Rousseau
    0.86
     amour
    0.84
    Emile
    0.82
    了口气
    0.80
     plaques
    0.79
    Chains
    0.78
     Julie
    0.78
    Activations Density 0.008%

    No Known Activations