© 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. 98867
    Prev
    Next
    INDEX
    Explanations

    Q marks

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

    This neuron fires on the kind of phrasing used in a board-game overview—specifically the “[Name] is a X-themed social deduction card game…” style of introduction.

    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
     filepath
    -0.74
     Золо
    -0.73
    ummies
    -0.72
    豪華
    -0.70
     phon
    -0.69
    poptotic
    -0.69
     Suivez
    -0.68
     Kein
    -0.67
    mspace
    -0.66
     Leon
    -0.65
    POSITIVE LOGITS
     xt
    0.83
    ₭
    0.83
    setProperty
    0.81
     matching
    0.80
    DEVICES
    0.80
     برنامه
    0.79
     cubes
    0.76
     植物
    0.75
     Mezz
    0.75
    yně
    0.74
    Activations Density 0.010%

    No Known Activations