© 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. 129229
    Prev
    Next
    INDEX
    Explanations

    collision detection and screen bounds

    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
     hockey
    -0.06
    village
    -0.06
     softball
    -0.06
     Village
    -0.06
     leur
    -0.06
     village
    -0.06
    lil
    -0.06
    Village
    -0.06
    Sports
    -0.06
     soccer
    -0.06
    POSITIVE LOGITS
     از
    0.07
     لدى
    0.06
     exclusivement
    0.06
     from
    0.06
     відбувається
    0.06
    Clothing
    0.06
     याता
    0.06
     zweimal
    0.06
     إعادة
    0.06
    널
    0.06
    Activations Density 0.004%

    No Known Activations