© 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. 119547
    Prev
    Next
    INDEX
    Explanations

    embedding

    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
     back
    -0.07
    过去
    -0.06
    avec
    -0.06
     interchangeably
    -0.06
    peicher
    -0.06
    過去
    -0.06
    Build
    -0.06
     Nutrient
    -0.06
     freshly
    -0.06
    witch
    -0.06
    POSITIVE LOGITS
     カメラ
    0.07
     जब
    0.06
     tiap
    0.06
     Motion
    0.06
     מו
    0.06
    werp
    0.06
    だったので
    0.06
    Motion
    0.06
    カメラ
    0.06
    사에
    0.06
    Activations Density 0.002%

    No Known Activations