© 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. 34737
    Prev
    Next
    INDEX
    Explanations

    dolphins and whales

    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
     chicken
    -1.05
     chickens
    -0.99
     poultry
    -0.82
    кури
    -0.81
     tiro
    -0.75
     crawled
    -0.75
     Chicken
    -0.75
     craw
    -0.73
     gallina
    -0.73
    避難
    -0.72
    POSITIVE LOGITS
     whale
    2.14
     whales
    2.11
     dolphin
    1.81
     dolphins
    1.78
     Whale
    1.67
     Whales
    1.62
    whale
    1.52
     Dolphins
    1.43
    Dolphin
    1.41
     bottlen
    1.41
    Activations Density 0.026%

    No Known Activations