© 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. 117404
    Prev
    Next
    INDEX
    Explanations

    emphasis or degree

    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
     ইতিমধ্যেই
    -0.07
     (#
    -0.06
     ইতিমধ্যে
    -0.06
    गात
    -0.06
     ici
    -0.06
    Uses
    -0.06
    entation
    -0.06
     here
    -0.06
     join
    -0.05
     Uses
    -0.05
    POSITIVE LOGITS
     bread
    0.06
    ْنَ
    0.06
     alanı
    0.06
     sektör
    0.06
    wał
    0.06
    たちの
    0.06
    esehatan
    0.06
     made
    0.06
    setPointSize
    0.06
     ميد
    0.06
    Activations Density 0.008%

    No Known Activations