© 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. 116897
    Prev
    Next
    INDEX
    Explanations

    context refers to user identification or associated entities

    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
    Different
    -0.08
    different
    -0.07
     Different
    -0.07
     different
    -0.07
    異なる
    -0.07
     farklı
    -0.07
     DIFFERENT
    -0.07
    桡
    -0.06
     différents
    -0.06
     diferentes
    -0.06
    POSITIVE LOGITS
     no
    0.06
     Sumatera
    0.06
     чисто
    0.06
    arching
    0.06
     détach
    0.06
     mildly
    0.06
     tolerant
    0.05
     पचास
    0.05
     kogu
    0.05
    మే
    0.05
    Activations Density 0.003%

    No Known Activations