© 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. 81010
    Prev
    Next
    INDEX
    Explanations

    official letters and documents

    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
     truyền
    -0.83
    ゞ
    -0.82
     outwards
    -0.79
    undur
    -0.79
     ruhig
    -0.78
    lbrakk
    -0.77
     đức
    -0.77
    遵
    -0.77
     Outputs
    -0.75
     Nominal
    -0.75
    POSITIVE LOGITS
    guidelines
    1.02
     Letters
    0.99
     LETTERS
    0.96
    Letters
    0.94
     unseres
    0.90
    awesome
    0.88
     Aunque
    0.88
     letters
    0.86
    ludes
    0.86
     
    0.86
    Activations Density 0.048%

    No Known Activations