© 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. 103716
    Prev
    Next
    INDEX
    Explanations

    tight

    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
    Bretagne
    -0.85
    Lleg
    -0.80
    omenta
    -0.76
     Lý
    -0.73
    verick
    -0.71
    ifdef
    -0.71
     betweenstory
    -0.68
     trữ
    -0.68
    maior
    -0.67
     الظ
    -0.66
    POSITIVE LOGITS
     tight
    6.09
    Tight
    5.50
     Tight
    5.44
     tighter
    5.41
    tight
    5.28
     tighten
    4.84
     tightened
    4.69
     tightness
    4.47
     tightening
    4.25
     tightly
    4.00
    Activations Density 0.063%

    No Known Activations