© 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. 89937
    Prev
    Next
    INDEX
    Explanations

    Dub and words starting with Dub

    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
     Eber
    -0.77
     bum
    -0.74
     dishonesty
    -0.72
     stockpile
    -0.71
     mop
    -0.69
    すれば
    -0.69
     Rep
    -0.68
     низ
    -0.68
     properties
    -0.68
     Healthcare
    -0.67
    POSITIVE LOGITS
    dub
    1.31
     dub
    1.23
    iously
    1.21
    Dub
    1.15
     DUB
    1.12
    step
    1.09
    IOUS
    1.02
     Dub
    1.00
     Dube
    0.98
    ious
    0.97
    Activations Density 0.009%

    No Known Activations