© 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. 117905
    Prev
    Next
    INDEX
    Explanations

    // or comments

    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
     what
    -0.08
     ಕೇಂದ್ರ
    -0.07
     biti
    -0.06
    還是
    -0.06
     Exports
    -0.06
     steroids
    -0.06
     בשנת
    -0.06
     Dealing
    -0.05
     बेड
    -0.05
    加拿大
    -0.05
    POSITIVE LOGITS
     people
    0.06
     overarching
    0.06
    广泛
    0.06
     తీవ్ర
    0.06
    ্রমে
    0.06
    FUTURE
    0.06
    툼
    0.06
    ujące
    0.06
    ℹ
    0.06
     acesta
    0.06
    Activations Density 0.002%

    No Known Activations