© 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. 129951
    Prev
    Next
    INDEX
    Explanations

    co-stimulatory or co-inhibitory signals

    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
    вої
    -0.06
     ఇప్పటికే
    -0.06
     estup
    -0.06
     चौथा
    -0.06
    Applied
    -0.06
     Hausdorff
    -0.06
     ঢেউ
    -0.06
    님이
    -0.06
     तिच्या
    -0.06
    淞
    -0.05
    POSITIVE LOGITS
     सकारात्मक
    0.06
     facts
    0.06
     data
    0.06
     additional
    0.06
    ⁺
    0.06
    돕
    0.06
     אחר
    0.06
    idl
    0.06
     गैर
    0.06
    ختلف
    0.06
    Activations Density 0.004%

    No Known Activations