© 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. 118278
    Prev
    Next
    INDEX
    Explanations

    phosphorylation and phosphatase

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

    biochemical and programming terms, particularly related to proteins, enzymes, and coding libraries.

    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
    (';
    -0.87
     Ub
    -0.79
    ⚖
    -0.76
    estões
    -0.75
     biome
    -0.73
    ago
    -0.72
     CoreData
    -0.72
    RDF
    -0.71
    Court
    -0.71
    搓
    -0.70
    POSITIVE LOGITS
     CTC
    1.05
     Beam
    0.93
    CTC
    0.92
    ctc
    0.86
     BLANK
    0.81
    BLANK
    0.80
     beam
    0.77
    Jody
    0.76
    Beam
    0.76
     nucleus
    0.75
    Activations Density 0.021%

    No Known Activations