© 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. 128380
    Prev
    Next
    INDEX
    Explanations

    submitted on briefs or arguments

    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
    Students
    -0.06
    롬
    -0.06
    While
    -0.06
    然后
    -0.06
    affe
    -0.06
    ī
    -0.06
    ى
    -0.06
     siswa
    -0.06
    usually
    -0.06
    ölf
    -0.06
    POSITIVE LOGITS
     doble
    0.07
     all
    0.07
     любых
    0.07
     einzigen
    0.07
     toutes
    0.06
     সব
    0.06
     جميع
    0.06
     iki
    0.06
    旖
    0.06
    全ての
    0.06
    Activations Density 0.001%

    No Known Activations