© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130594
    Prev
    Next
    INDEX
    Explanations

    announces / confirms

    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
    
    -0.06
     utan
    -0.05
     prior
    -0.05
    expose
    -0.05
     निचले
    -0.05
     scores
    -0.05
     নিম্ন
    -0.05
    म्प्ट
    -0.05
    ynthetic
    -0.05
     claim
    -0.05
    POSITIVE LOGITS
     миру
    0.07
     כך
    0.07
    inertia
    0.06
    ತ್ನ
    0.06
     aliqua
    0.06
     Assay
    0.06
     assay
    0.06
     Secretaría
    0.06
    ړئ
    0.06
     terbatas
    0.06
    Activations Density 0.053%

    No Known Activations