© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    About Us / Course / Analysis

    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
     проблеми
    -0.74
    '}),
    -0.73
     Catho
    -0.71
    Caso
    -0.71
     Exchanges
    -0.69
     Tactics
    -0.68
     娜
    -0.67
    Inhoud
    -0.67
    ➋
    -0.66
     uitz
    -0.66
    POSITIVE LOGITS
    PageFactory
    1.03
    LogFactory
    0.85
    ORIES
    0.85
    Directory
    0.82
    נטרנט
    0.82
    result
    0.81
    脸上的
    0.81
    object
    0.80
    context
    0.79
     Directory
    0.79
    Activations Density 0.022%

    No Known Activations