© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118526
    Prev
    Next
    INDEX
    Explanations

    Eighth

    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
    เคราะห์
    -0.06
     নিবাস
    -0.06
     aforesaid
    -0.06
     macchina
    -0.06
    udukan
    -0.06
     lurking
    -0.06
     neutroph
    -0.06
     aforementioned
    -0.06
    しながら
    -0.06
     offending
    -0.06
    POSITIVE LOGITS
     jedną
    0.06
    has
    0.06
     उत्कृष्ट
    0.06
     동일
    0.06
     board
    0.06
    टेट
    0.06
    $}}
    0.06
     besides
    0.06
     включая
    0.06
     Eight
    0.05
    Activations Density 0.019%

    No Known Activations