© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76973
    Prev
    Next
    INDEX
    Explanations

    ecological environments

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

    descriptions of marine and aquatic ecosystems and organisms.

    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
     социали
    -0.84
    ronomy
    -0.82
     aquatic
    -0.82
     lembrar
    -0.80
     xấu
    -0.76
    taps
    -0.76
    -&
    -0.75
     Aquatic
    -0.75
     desempeño
    -0.74
    tilli
    -0.74
    POSITIVE LOGITS
    fauna
    0.94
     boulder
    0.86
     leben
    0.86
     macro
    0.81
    Ford
    0.80
    Ben
    0.79
    POM
    0.77
    ชาว
    0.77
     redox
    0.77
     manipulative
    0.74
    Activations Density 0.035%

    No Known Activations