© 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. 116900
    Prev
    Next
    INDEX
    Explanations

    links and tracking

    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
     här
    -0.06
    靠近
    -0.06
    空的
    -0.06
     देखेंगे
    -0.06
     declaración
    -0.06
    沿着
    -0.06
     এখানকার
    -0.06
    getSupported
    -0.06
     encuentra
    -0.06
    эс
    -0.06
    POSITIVE LOGITS
    deterministic
    0.06
     tracking
    0.06
    Through
    0.06
     scenarios
    0.06
     subsequently
    0.06
     Apostolic
    0.06
     Subsequently
    0.06
    飚
    0.06
     乀
    0.06
    football
    0.06
    Activations Density 0.002%

    No Known Activations