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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90715
    Prev
    Next
    INDEX
    Explanations

    Resident Evil, Animal Crossing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     コンパクト
    -0.88
     kain
    -0.75
    exus
    -0.75
     legend
    -0.73
    olev
    -0.73
     orchids
    -0.71
    pov
    -0.71
     legacy
    -0.71
    ajevo
    -0.71
    볼
    -0.71
    POSITIVE LOGITS
     villager
    1.51
     villagers
    1.49
     Animal
    1.48
    Animal
    1.35
     island
    1.25
     Nook
    1.19
    Island
    1.09
     Nintendo
    1.08
    animal
    1.05
    villa
    1.03
    Activations Density 0.005%

    No Known Activations