© 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. 129606
    Prev
    Next
    INDEX
    Explanations

    starting position or offset

    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
    statistical
    -0.06
     interes
    -0.06
     பகுதி
    -0.06
     statistical
    -0.06
     geographically
    -0.05
     DataType
    -0.05
    模式
    -0.05
     bass
    -0.05
     bracket
    -0.05
     queried
    -0.05
    POSITIVE LOGITS
     supplied
    0.06
    洁
    0.06
     convirt
    0.06
    약을
    0.06
     affecting
    0.06
     разум
    0.06
     ওসি
    0.06
    باد
    0.06
     fantástico
    0.06
     послу
    0.06
    Activations Density 0.002%

    No Known Activations