© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30934
    Prev
    Next
    INDEX
    Explanations

    peptide and amino acid sequences

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

    amino acid sequences and protein-related notation in scientific documents.

    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
     by
    -0.97
     first
    -0.92
     if
    -0.87
     ступен
    -0.87
     after
    -0.86
     has
    -0.82
     helped
    -0.81
     jumped
    -0.81
     whenever
    -0.80
     praised
    -0.79
    POSITIVE LOGITS
    absolutely
    1.02
     rozpo
    0.97
    amide
    0.96
    definitely
    0.96
    —-
    0.91
    ANAL
    0.88
    unfortunately
    0.87
    primarily
    0.87
    wasn
    0.87
    taken
    0.86
    Activations Density 0.023%

    No Known Activations