© 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. 34-GEMMASCOPE-RES-131K
    7. 49899
    Prev
    Next
    INDEX
    Explanations

    Miacora, Health-related, I Did

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

    numbers and dates in text, particularly those in formats like years, episode numbers, and version numbers.

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

    The neuron specifically fires on occurrences of the TV show title “Battlestar Galactica.”

    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
     reiterate
    -0.77
    चार
    -0.75
     Indiana
    -0.75
     Idaho
    -0.75
     ex
    -0.75
    Isabelle
    -0.73
    成都
    -0.73
    unordered
    -0.73
    mping
    -0.71
     Granada
    -0.71
    POSITIVE LOGITS
     Tyrol
    1.01
     cyl
    1.01
     Cyl
    0.95
     Adama
    0.90
     cinza
    0.80
    frak
    0.74
     YOUTUBE
    0.74
    Cyl
    0.73
     Fleet
    0.73
    Ἐ
    0.73
    Activations Density 0.010%

    No Known Activations