© 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. 10-GEMMASCOPE-RES-131K
    7. 65818
    Prev
    Next
    INDEX
    Explanations

    renal histology or html document

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

    repeating dashes, equal signs, or similar characters forming horizontal lines or dividers in documents.

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

    The neuron is primarily triggered by numeric tokens, especially sequences of digits and decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ,
    -1.88
    ७
    -1.59
    くなりました
    -1.56
    几十
    -1.54
     What
    -1.43
     procedente
    -1.43
     Otros
    -1.42
     Α
    -1.41
    Its
    -1.41
    (
    -1.41
    POSITIVE LOGITS
     acquisto
    1.80
     a
    1.77
    はこの
    1.55
     soste
    1.54
     peculi
    1.54
     tramont
    1.53
    ↵
    1.52
     tasca
    1.52
    ，”
    1.49
    鹇
    1.49
    Activations Density 0.010%

    No Known Activations