© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57523
    Prev
    Next
    INDEX
    Explanations

    language varieties and prestige

    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
    BrowserRouter
    -0.78
     смысл
    -0.77
    Préparation
    -0.77
    Crédit
    -0.75
    ◘
    -0.74
    IUM
    -0.73
    prior
    -0.73
    CommonModule
    -0.72
     theological
    -0.72
    SDK
    -0.72
    POSITIVE LOGITS
     prestige
    1.27
     speakers
    1.26
     speaker
    1.12
     prestigious
    1.12
     status
    1.00
    prestige
    0.99
    speakers
    0.98
     domains
    0.98
    speaker
    0.96
     varieties
    0.96
    Activations Density 0.026%

    No Known Activations