© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59496
    Prev
    Next
    INDEX
    Explanations

    role-playing game terms

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

    The neuron strongly activates on capitalized proper names—especially RPG‐related titles, system names, publishers, and author names.

    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
     its
    -1.26
     новые
    -1.24
    berra
    -1.20
    oved
    -1.16
    气质
    -1.15
     molti
    -1.15
    Its
    -1.13
    ⁹
    -1.13
     ...
    -1.13
    ihnachts
    -1.10
    POSITIVE LOGITS
     like
    1.32
     gustado
    1.29
     you
    1.29
     menyiapkan
    1.24
     salido
    1.23
     jugado
    1.23
     membag
    1.22
     membeli
    1.21
     &
    1.20
    靱
    1.20
    Activations Density 0.015%

    No Known Activations