© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48833
    Prev
    Next
    INDEX
    Explanations

    multiple interconnected stories

    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
     when
    -0.96
     along
    -0.86
     hundreds
    -0.84
     regions
    -0.84
     вд
    -0.80
     lượng
    -0.78
    학
    -0.78
     both
    -0.78
     describes
    -0.77
     gases
    -0.77
    POSITIVE LOGITS
     interconnected
    1.53
     intertw
    1.45
     interrelated
    1.27
     stories
    1.24
    それぞれの
    1.23
     separate
    1.23
     disparate
    1.23
     vignette
    1.20
     różnych
    1.20
     intertwined
    1.20
    Activations Density 0.035%

    No Known Activations