© 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. 117835
    Prev
    Next
    INDEX
    Explanations

    certain prefixes for categories

    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
     that
    -0.07
    如果
    -0.07
     against
    -0.07
     Against
    -0.07
     如果
    -0.06
     That
    -0.06
    లతో
    -0.06
     असलेल्या
    -0.06
     through
    -0.06
     indefinitely
    -0.06
    POSITIVE LOGITS
     establish
    0.07
     lựa
    0.07
     its
    0.07
     renferme
    0.06
     sits
    0.06
    Its
    0.06
     Биз
    0.06
     escritório
    0.06
     establecer
    0.06
     sorta
    0.06
    Activations Density 0.001%

    No Known Activations