© 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. 107414
    Prev
    Next
    INDEX
    Explanations

    Kickstarter

    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
     Influenza
    -0.84
    Friction
    -0.77
     transversal
    -0.75
    Safari
    -0.69
    Flu
    -0.69
    Convenient
    -0.68
    improving
    -0.67
     influenza
    -0.66
     modifi
    -0.65
     упражнения
    -0.65
    POSITIVE LOGITS
     crowdfunding
    4.41
     Kickstarter
    4.28
     crowd
    4.06
     crow
    3.86
     Crow
    3.67
    crow
    3.61
     crowds
    3.41
    crowd
    3.38
    Crow
    3.33
     Crowd
    3.20
    Activations Density 0.068%

    No Known Activations