© 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. 82289
    Prev
    Next
    INDEX
    Explanations

    icosahedral geometry

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

    anatomical structures of viruses and particles, particularly related to icosahedral capsids.

    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
     stress
    -0.91
    CDA
    -0.85
    strains
    -0.85
     khu
    -0.84
     strcmp
    -0.79
     Stress
    -0.79
    stress
    -0.77
     Wester
    -0.77
     conced
    -0.76
    /]
    -0.75
    POSITIVE LOGITS
     Caspar
    1.03
     iko
    0.94
    hex
    0.82
    Hex
    0.82
    cosa
    0.78
    icos
    0.75
     Iva
    0.74
     Verbal
    0.74
     ico
    0.74
     Twelve
    0.73
    Activations Density 0.059%

    No Known Activations