© 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. 128846
    Prev
    Next
    INDEX
    Explanations

    list element indexing

    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
    今後の
    -0.07
     आइसलैंड
    -0.07
     situación
    -0.06
    斜
    -0.06
    Acknowled
    -0.06
     future
    -0.06
    进行
    -0.06
    στη
    -0.06
    appré
    -0.06
    বয়
    -0.06
    POSITIVE LOGITS
     create
    0.06
    РС
    0.06
     Create
    0.06
     thượng
    0.06
    imum
    0.05
     must
    0.05
     einde
    0.05
    мога
    0.05
     creates
    0.05
     deoarece
    0.05
    Activations Density 0.002%

    No Known Activations