© 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. 83749
    Prev
    Next
    INDEX
    Explanations

    past, present and future

    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
     propOrder
    -0.97
    行きます
    -0.91
      
    -0.91
    stwie
    -0.90
    later
    -0.89
     AssemblyTitle
    -0.88
     одного
    -0.88
    having
    -0.88
    キレイ
    -0.86
     पहले
    -0.86
    POSITIVE LOGITS
     glories
    1.64
     tense
    1.61
    rami
    1.45
     participle
    1.34
     decade
    1.27
     glory
    1.23
     few
    1.16
     history
    1.09
     Tense
    1.06
     maleta
    1.04
    Activations Density 0.018%

    No Known Activations