© 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. 73527
    Prev
    Next
    INDEX
    Explanations

    anaerobic methane hydrogen halogen

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

    scientific terms related to bacteria and microbial processes, especially in anaerobic conditions.

    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
    ndice
    -0.79
    Altura
    -0.79
    ixin
    -0.72
    ьа
    -0.72
     Réunion
    -0.71
     reunion
    -0.70
     mgr
    -0.70
     ALE
    -0.69
     interviewer
    -0.69
     jellyfish
    -0.69
    POSITIVE LOGITS
     anaerobic
    1.12
     hydrogen
    0.93
    的方向
    0.91
    Hydrogen
    0.91
    Ana
    0.89
     Schönheit
    0.80
    嫌
    0.77
     rumen
    0.76
     DIET
    0.75
     Ana
    0.75
    Activations Density 0.093%

    No Known Activations