© 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. 108099
    Prev
    Next
    INDEX
    Explanations

    back and forth

    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
    presso
    -0.85
    Excerpt
    -0.82
     Nó
    -0.73
     senaste
    -0.72
    Cass
    -0.71
     competent
    -0.71
     maging
    -0.71
    :~
    -0.71
    omination
    -0.70
    hdessä
    -0.69
    POSITIVE LOGITS
     forth
    2.42
     basics
    1.41
    forth
    1.21
     Basics
    1.11
     back
    1.02
    basics
    0.98
    Basics
    0.96
     again
    0.93
     Back
    0.93
     square
    0.91
    Activations Density 0.018%

    No Known Activations