© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33071
    Prev
    Next
    INDEX
    Explanations

    clearance, B grade, overstock, surplus items

    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
     besök
    -0.87
     Definitive
    -0.84
    ssp
    -0.79
     definitivo
    -0.79
     Preserve
    -0.78
     reinstalling
    -0.77
    頼
    -0.77
    個室
    -0.75
     hroz
    -0.74
    اط
    -0.74
    POSITIVE LOGITS
     clearance
    2.11
     Clearance
    1.77
     surplus
    1.74
    clearance
    1.69
     leftover
    1.53
     seconds
    1.51
     excess
    1.46
     discounted
    1.38
     uns
    1.35
     leftovers
    1.34
    Activations Density 0.036%

    No Known Activations