© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119003
    Prev
    Next
    INDEX
    Explanations

    sensation seeking

    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
     সরঞ্জাম
    -0.08
    ]【
    -0.07
    都没有
    -0.06
     cirrh
    -0.06
     Cuando
    -0.06
     проводят
    -0.06
    都沒有
    -0.06
    "]')
    -0.06
     desde
    -0.06
     مِن
    -0.06
    POSITIVE LOGITS
     boo
    0.06
     vrsta
    0.06
     ably
    0.06
    ambulance
    0.06
     banker
    0.06
     असलेली
    0.06
     alegre
    0.05
    coupled
    0.05
     solitary
    0.05
     lion
    0.05
    Activations Density 0.019%

    No Known Activations