© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55757
    Prev
    Next
    INDEX
    Explanations

    health and social issues

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

    prepositions and function words, particularly focusing on "of", "with", "about", "at", and "as" in academic or formal text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects and highlights numeric tokens—literal numbers and numeric measurements—in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    壟
    -0.93
    分けて
    -0.90
     detención
    -0.89
    owi
    -0.89
     raha
    -0.87
     perro
    -0.86
     kroner
    -0.85
     SCALE
    -0.85
    メーター
    -0.84
     ovale
    -0.84
    POSITIVE LOGITS
     politicians
    1.06
     some
    0.98
     individuals
    0.96
     informal
    0.94
     those
    0.90
     so
    0.89
     established
    0.88
     imported
    0.88
     political
    0.88
     educated
    0.88
    Activations Density 0.015%

    No Known Activations