© 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. 110732
    Prev
    Next
    INDEX
    Explanations

    differential spots

    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
     Atoms
    -0.83
     architects
    -0.75
    ragan
    -0.74
    Varint
    -0.73
     Ego
    -0.73
    owaniu
    -0.72
    Designer
    -0.72
     Rin
    -0.71
     préféré
    -0.70
     sche
    -0.70
    POSITIVE LOGITS
     spot
    1.22
     spots
    1.10
     differential
    1.08
    spots
    1.05
     DIG
    1.01
     Spots
    0.96
    spot
    0.96
     Spot
    0.93
     spotted
    0.93
     Differential
    0.93
    Activations Density 0.125%

    No Known Activations