© 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. 34-GEMMASCOPE-RES-131K
    7. 108004
    Prev
    Next
    INDEX
    Explanations

    role-playing game adventures

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

    This neuron strongly activates on tabletop role-playing–game terminology—words referring to things like maps, dungeons, monsters, characters, and similar RPG elements.

    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
    circle
    -0.76
    ouri
    -0.76
    録画
    -0.75
    sieme
    -0.73
     strategis
    -0.73
     International
    -0.73
     rows
    -0.73
    universe
    -0.72
     LOL
    -0.72
     lol
    -0.72
    POSITIVE LOGITS
     adventure
    1.91
    adventure
    1.63
    Adventure
    1.48
     encounter
    1.34
     adventures
    1.31
     NPCs
    1.27
     encounters
    1.23
     aventura
    1.20
    Encounter
    1.16
     scenario
    1.13
    Activations Density 0.027%

    No Known Activations