© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70071
    Prev
    Next
    INDEX
    Explanations

    private, privately, family

    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
    쉘
    -0.99
     durchschnitt
    -0.92
     cualquiera
    -0.88
    ctan
    -0.86
     imprescindible
    -0.86
     promotions
    -0.84
     inflow
    -0.83
     estrenar
    -0.82
    不支持
    -0.82
     necesarios
    -0.81
    POSITIVE LOGITS
     private
    1.77
    private
    1.57
     privately
    1.51
     family
    1.25
     at
    1.24
     privato
    1.23
    Private
    1.22
     Private
    1.20
     PRIVATE
    1.20
    priv
    1.16
    Activations Density 0.001%

    No Known Activations