© 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. 115496
    Prev
    Next
    INDEX
    Explanations

    marine mammals and emulators

    np_acts-logits-general · gemini-2.5-flash-lite

    references to marine mammals such as dolphins, whales, orcas, and cetaceans.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Concentration
    -0.78
    Martial
    -0.75
    Sailing
    -0.74
    annica
    -0.73
    Samurai
    -0.73
     yellow
    -0.73
    GIRLS
    -0.73
    enderung
    -0.72
    Etern
    -0.71
    illons
    -0.71
    POSITIVE LOGITS
     dolphin
    1.36
     Dolphin
    1.32
     dolphins
    1.27
     trainers
    1.26
     trainer
    1.18
    🐬
    1.12
    Sea
    1.12
     Dolphins
    1.11
     Trainer
    1.08
    Jump
    1.02
    Activations Density 0.015%

    No Known Activations