© 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. 118564
    Prev
    Next
    INDEX
    Explanations

    public spaces

    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
    对
    -0.07
    对他
    -0.07
    際には
    -0.06
    보는
    -0.06
     都
    -0.06
    -0.06
    對
    -0.06
    પાસ
    -0.06
     pratiquer
    -0.06
    colorful
    -0.06
    POSITIVE LOGITS
     recommended
    0.07
     instit
    0.07
     पांव
    0.07
     વિસ્ત
    0.06
     பொது
    0.06
     שני
    0.06
     superseded
    0.06
     advisable
    0.06
     détails
    0.06
     improvements
    0.06
    Activations Density 0.020%

    No Known Activations