© 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. 90952
    Prev
    Next
    INDEX
    Explanations

    links to specific resources

    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
     thousands
    -1.01
     Thousands
    -0.86
     until
    -0.85
    Thousands
    -0.82
    人参
    -0.72
    ambu
    -0.72
     Until
    -0.72
     discover
    -0.71
    と思っています
    -0.71
    Until
    -0.71
    POSITIVE LOGITS
    ury
    0.85
     Mosque
    0.84
    alamu
    0.84
     سور
    0.81
    Shipped
    0.79
    IEnumerator
    0.78
    ۪
    0.77
     domy
    0.77
    sukienka
    0.76
     Irland
    0.76
    Activations Density 0.057%

    No Known Activations