© 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. 83010
    Prev
    Next
    INDEX
    Explanations

    sample

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

    The neuron fires on the highly technical, detail-rich language of scientific methods sections—especially inorganic‐chemistry experimental procedures and data descriptions.

    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
    eader
    -0.89
    atakan
    -0.88
     PCV
    -0.87
    }}%
    -0.86
     INCLUDED
    -0.84
     插入
    -0.84
    koła
    -0.83
    ługość
    -0.82
    ukary
    -0.82
    Cade
    -0.81
    POSITIVE LOGITS
     samples
    2.17
     sample
    2.06
     Samples
    1.66
    Samples
    1.63
    Sample
    1.59
     Sample
    1.57
    samples
    1.55
    sample
    1.55
    样
    1.41
    SAMPLE
    1.37
    Activations Density 0.097%

    No Known Activations