© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82965
    Prev
    Next
    INDEX
    Explanations

    news report pairings

    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
     personalisation
    -0.82
    redhat
    -0.81
    localisation
    -0.80
    ък
    -0.75
     dollari
    -0.75
    syd
    -0.74
    gaan
    -0.74
    אט
    -0.73
    Provin
    -0.73
    アプリケーション
    -0.71
    POSITIVE LOGITS
     shielded
    0.86
     shielding
    0.82
     key
    0.80
     scientific
    0.80
    ValueGenerated
    0.79
     household
    0.78
    corso
    0.78
     government
    0.77
     centi
    0.77
     shield
    0.77
    Activations Density 0.004%

    No Known Activations