© 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. 10-GEMMASCOPE-RES-131K
    7. 103721
    Prev
    Next
    INDEX
    Explanations

    steampunk, warfare, cyber, shell, divergent

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

    video game titles and franchises, especially action games and first-person shooters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on words that are part of proper-noun titles for entertainment media (e.g. video games, movies, books).

    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
     these
    -1.59
     “
    -1.56
    ”)
    -1.55
    istungen
    -1.52
    ...”
    -1.46
     this
    -1.45
    ”.
    -1.39
    ”).
    -1.38
     “(
    -1.37
     they
    -1.34
    POSITIVE LOGITS
    苼
    1.76
    CÓMO
    1.47
    珢
    1.43
    Extremely
    1.41
     umiejęt
    1.37
    ஂ
    1.37
    䛗
    1.37
    vý
    1.35
    Workers
    1.34
     ſu
    1.33
    Activations Density 0.014%

    No Known Activations