© 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. 10-GEMMASCOPE-RES-131K
    4. 119624
    Prev
    Next
    INDEX
    Explanations

    songs by, air sorting

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

    This neuron detects forum-style quotation headers or attributions (e.g. lines like “Username wrote:” or “Someone said:”).

    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
     The
    -1.45
    ↵↵
    -1.38
     setelah
    -1.37
    {
    -1.34
     we
    -1.33
    много
    -1.32
     on
    -1.27
    imageshack
    -1.26
     после
    -1.22
    ष्य
    -1.22
    POSITIVE LOGITS
    -
    1.54
     such
    1.53
    annique
    1.50
    :
    1.50
     pâtes
    1.47
     oeufs
    1.47
     TIPO
    1.42
    offering
    1.38
     simult
    1.38
     couvre
    1.38
    Activations Density 0.022%

    No Known Activations