© 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. 73384
    Prev
    Next
    INDEX
    Explanations

    thousands of offers

    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
     two
    -1.32
     three
    -1.19
     or
    -1.19
     four
    -1.16
     sehr
    -1.13
     warum
    -1.07
     using
    -1.05
     during
    -1.02
     people
    -0.96
     there
    -0.95
    POSITIVE LOGITS
     thousands
    1.67
    thousands
    1.45
     milliers
    1.33
    Thousands
    1.32
     popular
    1.29
    popular
    1.26
     hund
    1.22
     Thousands
    1.22
     thousand
    1.20
    hundreds
    1.20
    Activations Density 0.074%

    No Known Activations