© 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. 128653
    Prev
    Next
    INDEX
    Explanations

    reviews and recommendations

    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
    但是
    -0.07
     большинства
    -0.07
    Dol
    -0.07
     moles
    -0.06
     wrongly
    -0.06
    仅仅
    -0.06
    由于
    -0.06
    已
    -0.06
    缺乏
    -0.06
    Invalid
    -0.06
    POSITIVE LOGITS
     trois
    0.07
     comme
    0.07
     drei
    0.06
     avec
    0.06
    いっぱい
    0.06
     like
    0.06
     a
    0.06
    很高
    0.06
    ющую
    0.06
     revisit
    0.06
    Activations Density 0.010%

    No Known Activations