© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129649
    Prev
    Next
    INDEX
    Explanations

    facebook presence

    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
     associates
    -0.06
     слабы
    -0.06
    pi
    -0.06
    setImageResource
    -0.05
    ellt
    -0.05
     কলকাত
    -0.05
    मता
    -0.05
     Welcome
    -0.05
     따라서
    -0.05
    ವ್
    -0.05
    POSITIVE LOGITS
     innovative
    0.07
     arcane
    0.06
     analytical
    0.06
     esoteric
    0.06
    Highly
    0.06
     touted
    0.06
    रासायनिक
    0.06
     método
    0.06
     Highly
    0.06
    墘
    0.06
    Activations Density 0.007%

    No Known Activations