© 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. 120438
    Prev
    Next
    INDEX
    Explanations

    numbers and questions

    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
     গিয়াছে
    -0.07
     Karnataka
    -0.06
     ঝুঁ
    -0.06
    కాల
    -0.06
     Neel
    -0.06
     closer
    -0.06
     ponte
    -0.06
     Jira
    -0.06
     souvent
    -0.06
     practitioner
    -0.06
    POSITIVE LOGITS
    Because
    0.08
     Because
    0.07
    ⎛
    0.06
     expressing
    0.06
    version
    0.06
     because
    0.05
    After
    0.05
     इंग्लिश
    0.05
     একদম
    0.05
    Så
    0.05
    Activations Density 0.001%

    No Known Activations