© 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. 47630
    Prev
    Next
    INDEX
    Explanations

    scientific symbols and citations

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

    square brackets in scientific papers containing citations or mathematical notation.

    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
     developing
    -0.84
     Schicks
    -0.83
     Kommentare
    -0.76
    と
    -0.74
    Thanksgiving
    -0.74
     유
    -0.73
    Developing
    -0.73
    menina
    -0.71
     νο
    -0.71
     develops
    -0.71
    POSITIVE LOGITS
    Título
    0.82
    EVAL
    0.79
    lovakia
    0.77
    popular
    0.75
     LAWRENCE
    0.74
    isher
    0.72
    phous
    0.72
     PLACES
    0.71
     "..\..\
    0.71
    inel
    0.71
    Activations Density 0.007%

    No Known Activations