© 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. 110699
    Prev
    Next
    INDEX
    Explanations

    falling and collapsing

    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
    tifiz
    -0.86
     rayas
    -0.79
    logía
    -0.78
     DELHI
    -0.77
     viewDidLoad
    -0.76
    痪
    -0.75
    .{
    -0.74
     상세
    -0.73
     Hodgson
    -0.73
    ecute
    -0.73
    POSITIVE LOGITS
     collapse
    2.33
     collapses
    2.27
     collapsing
    2.14
     collapsed
    2.11
     slump
    2.02
     dropping
    2.00
     flop
    1.91
     falling
    1.88
     slumped
    1.87
    collapse
    1.85
    Activations Density 0.024%

    No Known Activations