© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108304
    Prev
    Next
    INDEX
    Explanations

    my notes or male infertility

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

    content in classical literature, Greek mythology, and ancient texts.

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

    The neuron responds to archaic or elevated narrative language—especially Early Modern English pronouns and function words (e.g. “I,” “thy,” “thou,” “me,” “the,” etc.) in poetic or mythic contexts.

    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
    Quit
    -0.87
     Quit
    -0.80
    bereiche
    -0.78
     Spit
    -0.78
    adaş
    -0.78
     Azerbai
    -0.76
    VPS
    -0.76
    pora
    -0.73
     Marisa
    -0.73
     Marta
    -0.73
    POSITIVE LOGITS
     Antig
    0.97
     city
    0.94
     Oedipus
    0.92
    edipus
    0.92
     Thebes
    0.90
     Walgreens
    0.86
     blind
    0.85
    Tire
    0.84
    sandalias
    0.80
    Deque
    0.78
    Activations Density 0.018%

    No Known Activations