© 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. 118235
    Prev
    Next
    INDEX
    Explanations

    inflatable slides, branded tents, dry activities

    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
     immutable
    -0.79
     Surv
    -0.77
    hound
    -0.74
    JOURNAL
    -0.73
     carb
    -0.72
     lockers
    -0.71
     mmol
    -0.70
     overflows
    -0.69
    sold
    -0.69
    了几
    -0.69
    POSITIVE LOGITS
     inflatable
    1.63
     bounce
    1.20
    Infl
    1.16
     Infl
    1.07
    ouncy
    1.05
     bouncy
    0.96
     slide
    0.96
     party
    0.95
    bounce
    0.93
     rentals
    0.92
    Activations Density 0.010%

    No Known Activations