© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130688
    Prev
    Next
    INDEX
    Explanations

    Pokémon Go success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comparison
    -0.06
     webinars
    -0.06
     срав
    -0.06
    qualität
    -0.06
     مرت
    -0.06
     சிறந்த
    -0.06
    するとき
    -0.06
     supere
    -0.06
     Shee
    -0.06
     dossiers
    -0.06
    POSITIVE LOGITS
     damaged
    0.07
     repairing
    0.07
    相关
    0.07
     repair
    0.06
     daños
    0.06
     distanciation
    0.06
     damage
    0.06
     പഴയ
    0.05
     mayhem
    0.05
     चोरी
    0.05
    Activations Density 0.005%

    No Known Activations