© 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. 128568
    Prev
    Next
    INDEX
    Explanations

    watching or seen events

    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
     blueprints
    -0.07
     Rankings
    -0.07
     작업
    -0.06
     Specialist
    -0.06
     होगा
    -0.06
     전망
    -0.06
     sẽ
    -0.06
     Specialists
    -0.06
     restricts
    -0.06
     will
    -0.06
    POSITIVE LOGITS
     laissé
    0.07
     during
    0.07
    場面
    0.07
     watching
    0.06
    Эти
    0.06
     участия
    0.06
     Эти
    0.06
     primjer
    0.06
    watching
    0.06
     afternoons
    0.06
    Activations Density 0.009%

    No Known Activations