© 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. 116375
    Prev
    Next
    INDEX
    Explanations

    location, proposal, or new concept

    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
    Preparing
    -0.07
     potencialmente
    -0.07
     ожида
    -0.07
     When
    -0.07
     esperando
    -0.07
     preparing
    -0.07
     anticipating
    -0.07
     Hoping
    -0.07
     soon
    -0.07
     anticipates
    -0.07
    POSITIVE LOGITS
    ALTERN
    0.06
     costs
    0.06
     éléments
    0.06
     costos
    0.06
    ometries
    0.06
     justified
    0.06
     costing
    0.05
    包含了
    0.05
    方法
    0.05
     방식
    0.05
    Activations Density 0.007%

    No Known Activations