© 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. 119095
    Prev
    Next
    INDEX
    Explanations

    beach related words

    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
     abstin
    -1.02
    ële
    -0.96
    ométrie
    -0.95
     Auß
    -0.94
    behälter
    -0.93
     indiv
    -0.92
     Outdoors
    -0.88
    Router
    -0.87
     Exterior
    -0.86
     leaky
    -0.85
    POSITIVE LOGITS
     sand
    1.34
     shallow
    1.13
    sand
    1.05
     umbrellas
    1.03
     facilities
    0.96
     cát
    0.92
     volleyball
    0.90
     pebbles
    0.90
     rocks
    0.90
     sandy
    0.88
    Activations Density 0.009%

    No Known Activations