© 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. 100628
    Prev
    Next
    INDEX
    Explanations

    games like Mass Effect, BioWare, Citadel, Shepard, Guild Wars

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

    The neuron strongly activates on proper names and titles related to video games—e.g. game titles, developer/studio names, character or location 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
    lectro
    -1.26
     situado
    -1.20
    Perú
    -1.20
     rač
    -1.20
    ítő
    -1.20
    我們的
    -1.19
    ार्थ
    -1.19
    moncler
    -1.18
    いている
    -1.16
     Konkur
    -1.13
    POSITIVE LOGITS
     incluso
    1.17
     tuvo
    1.13
    陶
    1.12
     questi
    1.03
     nawet
    1.02
    étaro
    1.01
     >
    1.00
     doubt
    0.98
    ?
    0.98
    f
    0.98
    Activations Density 0.017%

    No Known Activations