© 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. 92010
    Prev
    Next
    INDEX
    Explanations

    coral reef

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

    references to coral in text, whether as a marine organism, color, or proper noun.

    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
    後に
    -0.80
     meditating
    -0.79
     propriété
    -0.78
    킨
    -0.78
     sooooo
    -0.76
     Daerah
    -0.75
     adulto
    -0.72
     hydrologic
    -0.72
     działania
    -0.71
     earthen
    -0.71
    POSITIVE LOGITS
     reef
    1.82
     reefs
    1.62
    reef
    1.38
     Reef
    1.29
     Coral
    1.18
     coral
    1.09
    礁
    0.96
    SIM
    0.92
     Springs
    0.90
    ↼
    0.90
    Activations Density 0.013%

    No Known Activations