© 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. 118549
    Prev
    Next
    INDEX
    Explanations

    college recruiting news

    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
     سننے
    -0.08
     getRandom
    -0.07
     খুবই
    -0.06
     doubt
    -0.06
     కుటుంబ
    -0.06
     cujo
    -0.06
     قاعد
    -0.06
    Its
    -0.06
     acquaintances
    -0.06
    pessoas
    -0.06
    POSITIVE LOGITS
     sometimes
    0.06
     Powell
    0.06
     redux
    0.06
     often
    0.06
     alerted
    0.05
    oft
    0.05
     each
    0.05
    ногда
    0.05
    sometimes
    0.05
    美国
    0.05
    Activations Density 0.001%

    No Known Activations